Search
Type in the search box to filter 383 jobs, tools, skills, prompts, workflows, articles and repos.
Staff Frontier Agents Engineer (Forward Deployed Engineering)
Scale AI · San Francisco, CA; New York, NY
Senior Frontier Agents Engineer (Forward Deployed Engineering)
Scale AI · San Francisco, CA; New York, NY
Frontier Agents Engineer (Forward Deployed Engineering)
Scale AI · San Francisco, CA; New York, NY
Forward Deployed Infrastructure Engineer, New Grad - UK Government
Palantir · London, United Kingdom
Discovery-to-brief in 15 minutes
5 steps: Get the customer's consent before recording, then record with a notetaker your company has approved (e.g. Fathom, Granola). If there is no recording, use your typed notes.
Show details
1. Get the customer's consent before recording, then record with a notetaker your company has approved (e.g. Fathom, Granola). If there is no recording, use your typed notes. 2. Paste the transcript into your AI tool with the 'deal summary' prompt. 3. Ask it to list every assumption not stated by the customer. 4. Fix gaps with the user, then generate a 5-bullet brief for the AE and a follow-up email draft (use the second prompt). Do not send the email. 5. The user logs the brief in CRM and sets next-step dates.
Account research before first call
5 steps: Ask the user to paste the company's public info (site pages, latest 10-K or press releases) and the attendees' titles. If you have web access, you may read public pages yourself; cite the URL for every fact. Do not scrape LinkedIn.
Show details
1. Ask the user to paste the company's public info (site pages, latest 10-K or press releases) and the attendees' titles. If you have web access, you may read public pages yourself; cite the URL for every fact. Do not scrape LinkedIn. 2. Summarize business model, recent changes and likely priorities. Label every inferred pain or priority HYPOTHESIS. 3. Generate 10 discovery questions ranked by importance. 4. Flag 3 'not a fit' signals to watch for. 5. Return a one-page call plan with these sections: business model, recent changes, likely pains (hypotheses), 10 ranked questions, 3 not-a-fit signals, open questions.
Tailored demo in an hour
5 steps: List the top 3 pains from discovery.
Show details
1. List the top 3 pains from discovery. 2. Prompt the demo-story template to map pain → feature → outcome. 3. Generate fake but realistic demo data as CSV; the user loads it into their sandbox. 4. Run the 'pre-mortem my demo' prompt as the skeptical buyer. 5. Suggest the user record a 3-minute walkthrough (e.g. Loom) for async stakeholders.
POC scope that gets signed
5 steps: Draft the scope with the POC prompt (objective, criteria, timeline, owners).
Show details
1. Draft the scope with the POC prompt (objective, criteria, timeline, owners). 2. Pressure-test each success criterion for measurability. 3. Review with the champion; agree on pass/fail before kickoff. 4. Turn the timeline into a shared checklist with dates. 5. Draft a recap email confirming criteria in writing for the user to review and send.
Agent POC with evals
5 steps: Pick one narrow task and collect 20–50 real example inputs (with permission).
Show details
1. Pick one narrow task and collect 20–50 real example inputs (with permission). 2. Build the first version with an agent framework (e.g. LangGraph, OpenAI Agents SDK). 3. Write expected outputs and pass/fail checks for each input (first prompt), then run them through an eval tool (e.g. promptfoo, now part of OpenAI and still MIT open source, or DeepEval). 4. Trace failures with an observability tool (e.g. Langfuse, now part of ClickHouse and still open source, or LangSmith). 5. Report pass rate against the agreed criteria with the second prompt, not vibes. A zero-tolerance check that fails means the POC fails, whatever the average.
Security questionnaire first pass
5 steps: Gather your approved security docs (SOC 2 summary, DPA, architecture).
Show details
1. Gather your approved security docs (SOC 2 summary, DPA, architecture). 2. Prompt the AI to answer only from those docs and mark gaps NEEDS REVIEW. 3. Route NEEDS REVIEW items to security/legal owners. 4. Store final, approved answers in your RFP tool (e.g. Loopio, or Responsive, formerly RFPIO) for reuse. 5. Track turnaround time per questionnaire.
Discovery call prep
I have a discovery call with [COMPANY], a [INDUSTRY] company, with [ROLE OF ATTENDEES]. Our product does [ONE-LINE PRODUCT]. Using only publ
Show prompt
I have a discovery call with [COMPANY], a [INDUSTRY] company, with [ROLE OF ATTENDEES]. Our product does [ONE-LINE PRODUCT]. Using only public info I paste below, list: 5 likely business pains, 10 open-ended discovery questions ranked by importance, and 3 signals that this is NOT a fit. Info: [PASTE]
Turn call notes into a deal summary
Here are raw notes from a discovery call: [PASTE]. Rewrite them as: current state, desired outcome, metrics they care about, decision proces
Show prompt
Here are raw notes from a discovery call: [PASTE]. Rewrite them as: current state, desired outcome, metrics they care about, decision process, technical environment, risks, and open questions. Flag anything I assumed but they did not say.
Map the stakeholders
From this email thread and call notes [PASTE], build a stakeholder map: name, title, what they care about, likely objection, influence (high
Show prompt
From this email thread and call notes [PASTE], build a stakeholder map: name, title, what they care about, likely objection, influence (high/med/low). Suggest one question to ask each person next.
Build a tailored demo story
Our product features: [LIST]. Prospect pains from discovery: [LIST]. Build a 20-minute demo flow: opening hook tied to their top pain, 3 sce
Show prompt
Our product features: [LIST]. Prospect pains from discovery: [LIST]. Build a 20-minute demo flow: opening hook tied to their top pain, 3 scenes (pain → feature → outcome), and a close asking for a specific next step. Cut any feature that doesn't map to a pain.
Generate realistic demo data
Generate 25 rows of realistic but fake sample data for a [INDUSTRY] demo of [USE CASE] as CSV with columns [COLUMNS]. Include 3 edge cases t
Show prompt
Generate 25 rows of realistic but fake sample data for a [INDUSTRY] demo of [USE CASE] as CSV with columns [COLUMNS]. Include 3 edge cases that would make the demo more convincing. No real company or person names.
Pre-mortem my demo
Here is my demo outline: [PASTE]. Act as a skeptical [BUYER ROLE]. List the 7 moments where you would lose interest or push back, and how I
Show prompt
Here is my demo outline: [PASTE]. Act as a skeptical [BUYER ROLE]. List the 7 moments where you would lose interest or push back, and how I should fix each.
What are Forward Deployed Engineers, and why are they so in demand?
Gergely Orosz on where the FDE role came from (Palantir's 'Deltas') and how OpenAI and Ramp run it today.
Forward Deployed Engineers
Marty Cagan argues FDEs work best when field learnings get turned into reusable platform capabilities.
Trading Margin for Moat: Why the FDE Is the Hottest Job in Startups
Why AI application companies accept lower early margins to embed engineers who make agents work in customer systems.
The Palantirization of everything
Where startups copying Palantir's forward-deployed model get the analogy right, and where it breaks.
Forward Deployed Engineering
How Ramp's engineering team describes its own forward deployed engineering function.
What is a forward deployed engineer? The job, the pay and who hires
A sourced explainer comparing the FDE, consultant and Deployment Strategist titles and who hires for each.
n8n-io/n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
firecrawl/firecrawl
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
ollama/ollama
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
langgenius/dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Prashant Lakhera (@lakhera2015)
🚀 Forward Deployed Engineer might be one of the most interesting roles to watch in the AI job market right now. A few years ago, when we talked about Forward D
Show details
🚀 Forward Deployed Engineer might be one of the most interesting roles to watch in the AI job market right now. A few years ago, when we talked about Forward Deployed Engineers, one company immediately came to mind: Palantir. That is changing very quickly. I spent some time
Data Science Dojo (@DataScienceDojo)
We're excited to have Aater Suleman, Co-founder of Vixul, Hannah Marlowe, Senior Director of AI Forward Deployed Engineering at Databricks, and Dan Maloney, CEO
Show details
We're excited to have Aater Suleman, Co-founder of Vixul, Hannah Marlowe, Senior Director of AI Forward Deployed Engineering at Databricks, and Dan Maloney, CEO of LandingAI, joining the panel "Secure AI Needs Forward Deployed Engineers" at the Agentic AI Conference! 🎙️ Secure,
Roc Rizzardini (@rocrizzardini)
You hired a forward deployed engineer to write code. The survey says the job is 31% code. The other 47% is why the role exists. Perspective AI surveyed 1,500 f
Show details
You hired a forward deployed engineer to write code. The survey says the job is 31% code. The other 47% is why the role exists. Perspective AI surveyed 1,500 forward deployed engineers at 154 companies, February to April 2026 (published May 18, 2026): 1. The median week: 47%
Mark Ajzenstadt (@mardehaym)
Hot take: forward-deployed engineering is overrated. Gartner predicts that by 2028, 70% of enterprises will abandon agentic AI built by vendor forward-deployed
Show details
Hot take: forward-deployed engineering is overrated. Gartner predicts that by 2028, 70% of enterprises will abandon agentic AI built by vendor forward-deployed engineers, citing rising costs and the inability to evolve those systems independently. I’ve spent over a decade
Alfin (@AlfinCodes)
Anthropic is hiring Forward Deployed Engineers (FDEs) But what the hell is a Forward Deployed Engineer?
Show details
Anthropic is hiring Forward Deployed Engineers (FDEs) But what the hell is a Forward Deployed Engineer?
The Adaptive Engineer (@zahiruddin_t)
Everyone talks about Forward Deployed Engineers at OpenAI, Anthropic, and Palantir. But I think there's an equally important role The Internal Forward Deployed
Show details
Everyone talks about Forward Deployed Engineers at OpenAI, Anthropic, and Palantir. But I think there's an equally important role The Internal Forward Deployed Engineer. The engineer who helps teams across an enterprise adopt AI.
Give the model the role and the reader
Say who it is writing as and for whom (e.g. 'a CFO who skims'). Output changes more from audience than from adjectives.
Show details
Say who it is writing as and for whom (e.g. 'a CFO who skims'). Output changes more from audience than from adjectives.
Paste the source, don't describe it
Paste call notes, docs or logs. Summaries of summaries lose the details that matter.
Show details
Paste call notes, docs or logs. Summaries of summaries lose the details that matter.
Ask it to flag gaps instead of guessing
Add 'If the input doesn't support an answer, write NEEDS REVIEW.' This cuts made-up details in customer-facing work.
Show details
Add 'If the input doesn't support an answer, write NEEDS REVIEW.' This cuts made-up details in customer-facing work.
Use structure for reusable outputs
Request fixed sections or a table so status updates and POC docs look the same every week.
Show details
Request fixed sections or a table so status updates and POC docs look the same every week.
Iterate in two passes
First ask for a draft, then ask it to critique the draft as the skeptical buyer, then revise.
Show details
First ask for a draft, then ask it to critique the draft as the skeptical buyer, then revise.
Keep a personal prompt library
Save prompts that worked with your [BRACKET] variables. Our prompts page is a starting point.
Show details
Save prompts that worked with your [BRACKET] variables. Our prompts page is a starting point.

What is a Forward Deployed Engineer? (with Founding Rippling FDE)
Aced (formerly Exponent) · YouTube

Palantir's Forward Deployed Software Engineer - Revolution or Rebrand? | AA218
Arguing Agile · YouTube
Cursor
AI code editor with an agent mode and a familiar VS Code feel.
- Our pickan editor first, agent second, so it's the gentlest start if you already code in VS Code.
- free plan: yes
Claude Code
Terminal and IDE coding agent from Anthropic that edits files, runs commands and opens PRs.
- Our pickruns in the terminal and reads skills from ~/.claude/skills, so our kit skills work in it directly.
- ★ 152,558 GitHub stars · last commit 2026-10-18 (GitHub API, 2026-10-19)
- free plan: no
OpenAI Codex CLI
OpenAI's open-source coding agent for the terminal.
- ★ 129,927 GitHub stars · last commit 2026-10-19 (GitHub API, 2026-10-19)
Aider
Open-source AI pair programmer in your terminal that commits changes to git.
- ★ 49,642 GitHub stars · last commit 2026-05-22 (GitHub API, 2026-10-19)
promptfoo
CLI for prompt and agent evals plus red-teaming, driven by a YAML config.
- Our pickopen source, runs locally from a config file, no account needed to try it.
- ★ 26,150 GitHub stars · last commit 2026-10-19 (GitHub API, 2026-10-19)
Langfuse
Open-source LLM tracing, prompt management and evals, cloud or self-hosted.
- Our pickopen-source tracing plus evals you can self-host when customer data can't leave their cloud.
- ★ 36,035 GitHub stars · last commit 2026-10-19 (GitHub API, 2026-10-19)
- free plan: yes
DeepEval
Pytest-style unit tests for LLM outputs with ready-made metrics.
- ★ 18,962 GitHub stars · last commit 2026-10-19 (GitHub API, 2026-10-19)
Arize Phoenix
Open-source tracing and eval workbench built on OpenTelemetry.
- ★ 11,911 GitHub stars · last commit 2026-10-19 (GitHub API, 2026-10-19)
Navattic
Interactive, click-through product demos built from captures of your app.
- Our pickclick-through demos with no code; already on our tools list.
- free plan: yes
Vercel AI SDK
TypeScript toolkit for streaming chat, tool calls and agent UIs.
- Our picka quick way to stand up a working AI app for a POC in TypeScript.
- ★ 27,402 GitHub stars · last commit 2026-10-19 (GitHub API, 2026-10-19)
Dify
Open-source platform for building LLM apps and agent workflows visually.
- ★ 158,915 GitHub stars · last commit 2026-10-19 (GitHub API, 2026-10-19)
Storylane
Interactive product demos and guided tours.
Granola
Notepad that adds AI notes to what you type in a meeting.
- Our picknotes on your own machine with no bot joining the call. Check your company approves it first.
- free plan: yes
Gong
Revenue intelligence: call recording, deal tracking and coaching across a sales team.
- Our pickteam-wide call recording and deal tracking, usually bought by the sales org.
- free plan: not listed
Grok Bot Outbound Prospecting template
Finds prospects that match your ideal customer and drafts a first message to each, for your review.
- Importable; every fact needs a source URL or stays blank, and it never sends without a yes. (template by Krista Letz)
Firecrawl
Turns websites into clean markdown or structured data for agents.
- Our pickturns company sites into clean text an agent can research from.
- ★ 193,069 GitHub stars · last commit 2026-10-19 (GitHub API, 2026-10-19)
- free plan: yes
browser-use
Open-source library that lets an AI agent drive a web browser.
- ★ 118,530 GitHub stars · last commit 2026-10-17 (GitHub API, 2026-10-19)
Crawl4AI
Open-source crawler that outputs LLM-ready markdown.
- ★ 85,853 GitHub stars · last commit 2026-10-19 (GitHub API, 2026-10-19)
Zapier
No-code automation across thousands of apps.
- Our pickhosted, huge app catalog, nothing to run.
- free plan: yes
n8n
Workflow automation with AI agent nodes, self-hosted or cloud.
- Our pickself-hostable with AI agent nodes, so it fits customers who keep data in-house.
- ★ 208,033 GitHub stars · last commit 2026-10-19 (GitHub API, 2026-10-19)
Run a discovery call that ends with clear pains, metrics and next step
Customer skill checklist item
Build a working integration end to end (API → data → output) and explain it
Customer skill checklist item
Scope a proof of concept
Draft a POC scope for [COMPANY] testing [PRODUCT] for [USE CASE]. Include: objective, 3–5 measurable success criteria, in/out of scope, data
Show prompt
Draft a POC scope for [COMPANY] testing [PRODUCT] for [USE CASE]. Include: objective, 3–5 measurable success criteria, in/out of scope, data and access needed from them, timeline by week, owners on both sides, and exit decision. Keep it to one page.
Pressure-test success criteria
Here are proposed POC success criteria: [PASTE]. For each, say if it is measurable, who measures it, how it could be gamed or misread, and r
Show prompt
Here are proposed POC success criteria: [PASTE]. For each, say if it is measurable, who measures it, how it could be gamed or misread, and rewrite vague ones into concrete pass/fail tests.
Data and security questionnaire prep
The customer sent this security/IT questionnaire: [PASTE]. Using our documentation [PASTE], draft answers. Mark any question where our docs
Show prompt
The customer sent this security/IT questionnaire: [PASTE]. Using our documentation [PASTE], draft answers. Mark any question where our docs don't clearly support an answer as NEEDS REVIEW instead of guessing.
Architecture explainer for execs
Explain this integration architecture [PASTE DIAGRAM DESCRIPTION OR NOTES] to a non-technical VP in under 200 words: what connects to what,
Show prompt
Explain this integration architecture [PASTE DIAGRAM DESCRIPTION OR NOTES] to a non-technical VP in under 200 words: what connects to what, where their data goes, and what their team has to do. No jargon without a plain-English gloss.
Write a solution design doc
Turn these notes into a solution design doc with sections: context, requirements, proposed design, integrations, data flow, security conside
Show prompt
Turn these notes into a solution design doc with sections: context, requirements, proposed design, integrations, data flow, security considerations, alternatives considered, open questions. Notes: [PASTE]
Debug log triage
Here is an error log from a customer environment: [PASTE]. Summarize what likely failed, the 3 most probable root causes in order, and the e
Show prompt
Here is an error log from a customer environment: [PASTE]. Summarize what likely failed, the 3 most probable root causes in order, and the exact next diagnostic step for each. Say clearly if the log is insufficient.
Objection response drafts
Prospect objection: "[OBJECTION]". Context: [DEAL CONTEXT]. Give 3 responses: one that asks a clarifying question, one that reframes with a
Show prompt
Prospect objection: "[OBJECTION]". Context: [DEAL CONTEXT]. Give 3 responses: one that asks a clarifying question, one that reframes with a business outcome, one that offers proof (POC, reference, doc). Keep each under 60 words.
Competitive positioning
We're competing with [COMPETITOR] for [USE CASE]. From the public info I paste [PASTE], list where they are genuinely stronger, where we are
Show prompt
We're competing with [COMPETITOR] for [USE CASE]. From the public info I paste [PASTE], list where they are genuinely stronger, where we are, and 4 discovery questions that surface our strengths honestly. Don't invent claims about them.
Build vs buy rebuttal
The customer's engineering team says they can build this in-house. Draft a respectful talk track covering total cost of ownership, time to v
Show prompt
The customer's engineering team says they can build this in-house. Draft a respectful talk track covering total cost of ownership, time to value, maintenance, and what they'd still own. Include 3 questions to quantify their build estimate.
30-60-90 implementation plan
Create a 30-60-90 day implementation plan for [CUSTOMER] deploying [PRODUCT] for [USE CASE] with [TEAM SIZE]. Include milestones, dependenci
Show prompt
Create a 30-60-90 day implementation plan for [CUSTOMER] deploying [PRODUCT] for [USE CASE] with [TEAM SIZE]. Include milestones, dependencies, customer-side owners, risks, and what 'live' means at day 90. Use TBD for any owner or date I haven't given you.
Risk register
From this project plan [PASTE], build a risk register table: risk, likelihood, impact, early warning sign, mitigation, owner. Add 3 risks th
Show prompt
From this project plan [PASTE], build a risk register table: risk, likelihood, impact, early warning sign, mitigation, owner. Add 3 risks the plan doesn't mention but deployments like this commonly hit, labeled GENERIC.
Runbook from tribal knowledge
Here's a messy Slack thread about how we set up [SYSTEM] for a customer: [PASTE]. Turn it into a numbered runbook with prerequisites, steps,
Show prompt
Here's a messy Slack thread about how we set up [SYSTEM] for a customer: [PASTE]. Turn it into a numbered runbook with prerequisites, steps, verification checks, and rollback steps. Mark anything the thread doesn't cover as GAP instead of filling it in.
Weekly customer status update
Write a weekly status email for [CUSTOMER] from these notes [PASTE]: green/yellow/red status, done this week, next week, blockers needing th
Show prompt
Write a weekly status email for [CUSTOMER] from these notes [PASTE]: green/yellow/red status, done this week, next week, blockers needing their action (with owner and date), decisions needed. Under 200 words.
Escalation email
Draft a calm escalation email to [CUSTOMER EXEC] about [ISSUE]: what happened, impact, what we've done, what we need from them, and the date
Show prompt
Draft a calm escalation email to [CUSTOMER EXEC] about [ISSUE]: what happened, impact, what we've done, what we need from them, and the date of the next update (use [DATE] if I haven't given one). No blame, no hedging.
Internal deal debrief
Summarize this deal for my internal team from these notes [PASTE]: why we won/lost, what the customer actually valued, product gaps raised (
Show prompt
Summarize this deal for my internal team from these notes [PASTE]: why we won/lost, what the customer actually valued, product gaps raised (each with a verbatim quote from the notes or "no quote", a theme, and the deal size), and 3 lessons for the next similar deal.
Executive business review
Draft an EBR outline for [CUSTOMER] after [N] months using these usage metrics and outcomes [PASTE]: goals vs results, value delivered, adop
Show prompt
Draft an EBR outline for [CUSTOMER] after [N] months using these usage metrics and outcomes [PASTE]: goals vs results, value delivered, adoption gaps, roadmap asks, and a proposed expansion next step. Only use the numbers provided.
AE brief and follow-up email
From this corrected deal summary [PASTE], write (1) a 5-bullet brief for my account executive: pain, deadline, must-haves, buying path, next
Show prompt
From this corrected deal summary [PASTE], write (1) a 5-bullet brief for my account executive: pain, deadline, must-haves, buying path, next step with date, and (2) a short follow-up email to the customer recapping what we heard and the agreed next steps. Use only facts in the summary.
Build the eval set
Here is the agent's task: [TASK]. Here are real example inputs, shared with permission: [PASTE]. For each input, write the expected output a
Show prompt
Here is the agent's task: [TASK]. Here are real example inputs, shared with permission: [PASTE]. For each input, write the expected output and 1-3 pass/fail checks a script or reviewer can apply. Mark ambiguous inputs AMBIGUOUS instead of choosing an answer, and list them for the customer to label.
Pass-rate report
Agreed criteria: [PASTE]. Eval results: [PASTE]. Report the pass rate for each criterion with counts (e.g. 27/30), say pass or fail against
Show prompt
Agreed criteria: [PASTE]. Eval results: [PASTE]. Report the pass rate for each criterion with counts (e.g. 27/30), say pass or fail against each threshold, list the failing ids, and give one concrete next fix. Use only the numbers provided. (To agree the criteria first, use the poc-scope-that-gets-signed skill.)
Integration debugging loop
5 steps: Reproduce the issue and capture logs, request/response and environment. Redact tokens, API keys, passwords and personal data before pasting anything into an AI tool.
Show details
1. Reproduce the issue and capture logs, request/response and environment. Redact tokens, API keys, passwords and personal data before pasting anything into an AI tool. 2. Paste logs into the triage prompt for ranked root causes. 3. The user tests the top hypothesis with Postman, curl or a small script, and pastes the result back. 4. Document the fix as a runbook entry. 5. Share a plain-English summary with the customer.
30-60-90 implementation plan
5 steps: Feed scope, team size and success criteria into the 30-60-90 prompt.
Show details
1. Feed scope, team size and success criteria into the 30-60-90 prompt. 2. Generate a risk register and add customer-specific risks. 3. Ask the user for customer-side owners for every dependency; write TBD where none is given. 4. The user reviews the plan in the kickoff meeting and gets explicit agreement. 5. Turn milestones into weekly status-update headings.
Weekly status update on autopilot
5 steps: Keep a running notes doc per customer during the week.
Show details
1. Keep a running notes doc per customer during the week. 2. Friday: paste notes into the status prompt (RAG status, done, next, blockers). 3. Check every owner and date is real. 4. Return the email as a draft. The user sends it and pins it in the shared channel. 5. Escalate any red item with the escalation prompt the same day.
Runbook from Slack chaos
5 steps: Export the relevant thread(s). Remove tokens, passwords and customer personal data first.
Show details
1. Export the relevant thread(s). Remove tokens, passwords and customer personal data first. 2. Prompt the AI to produce a numbered runbook with checks and rollback. 3. Follow the runbook yourself once on a test environment. 4. Fix steps that fail, then publish to your wiki. 5. Link the runbook in future tickets.
Deal debrief → product feedback
5 steps: After win/loss, paste notes into the debrief prompt.
Show details
1. After win/loss, paste notes into the debrief prompt. 2. Extract product gaps. Use only verbatim quotes that appear in the notes; if a gap has no quote, say so. 3. Group gaps by theme and deal size. 4. The user shares the gap list with product monthly in a single doc. 5. The user tracks which gaps ship and tells the customer.
EBR deck in an afternoon
5 steps: Export usage metrics and outcomes for the period.
Show details
1. Export usage metrics and outcomes for the period. 2. Prompt the EBR outline using only the provided numbers. 3. Ask the user for one real customer story; take one adoption gap from the data. Mark anything missing [NEEDED]. 4. Propose a specific next step grounded in the data; for commercial expansion, use the user's option and pricing, never invented numbers. 5. Rehearse with the champion before the exec meeting.
Discovery call to brief
kit skill discovery-to-brief-in-15-minutes
Try this first: /discovery-to-brief-in-15-minutes then paste your call notes.
- Kit skill + guide
Show prompt
Try this first: /discovery-to-brief-in-15-minutes then paste your call notes.
Account research before a first call
kit skill account-research-before-first-call
Try this first: Give it the company and the attendees' roles; get a one-page call plan with 10 ranked discovery questions.
- Kit skill + guide
Show prompt
Try this first: Give it the company and the attendees' roles; get a one-page call plan with 10 ranked discovery questions.
Weekly customer status update
kit skill weekly-status-update-on-autopilot
Try this first: Paste this week's notes and Slack threads; review the draft before it goes anywhere.
- Kit skill + guide
Show prompt
Try this first: Paste this week's notes and Slack threads; review the draft before it goes anywhere.
Prospecting list for review
Grok Bot Outbound Prospecting template (Krista Letz)
Try this first: Give it 5 target companies; it returns a sourced review list and sends nothing.
- Grok Bot template
Show prompt
Try this first: Give it 5 target companies; it returns a sourced review list and sends nothing.
Security questionnaire first pass
kit skill security-questionnaire-first-pass
Try this first: Paste the questionnaire plus your approved security docs; it answers only from them and marks gaps NEEDS REVIEW.
- Kit skill + guide
Show prompt
Try this first: Paste the questionnaire plus your approved security docs; it answers only from them and marks gaps NEEDS REVIEW.
Agent POC with evals
kit skill agent-poc-with-evals
Try this first: Start with 20-50 real example inputs; it walks you through the build, the evals and a pass-rate report.
- Kit skill + guide
Show prompt
Try this first: Start with 20-50 real example inputs; it walks you through the build, the evals and a pass-rate report.
Nightly prospecting routine
guide: prospecting-agent-setup.html (built on Grok Bot's official Sales Outbound use case)
Try this first: Run the prompt by hand once, then schedule it to stop at the review list.
- Guide
Show prompt
Try this first: Run the prompt by hand once, then schedule it to stop at the review list.
shadcn-ui/ui
Composable, accessible components with thoughtful defaults. Build your own component library with code you can customize, extend, and make your own.
browser-use/browser-use
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
supabase/supabase
The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.
unclecode/crawl4ai
Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key.
mem0ai/mem0
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
BerriAI/litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
crewAIInc/crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
anthropics/claude-cookbooks
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
langfuse/langfuse
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
mastra-ai/mastra
Mastra is the modern TypeScript framework for AI-powered applications and agents.
vercel/ai
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
promptfoo/promptfoo
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
modelcontextprotocol/python-sdk
The official Python SDK for Model Context Protocol servers and clients
google/adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
pydantic/pydantic-ai
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
pipecat-ai/pipecat
Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
A short history of the forward deployed engineer
A timeline from Palantir to the model labs to AI studios.
Building effective agents
Anthropic's patterns for agent systems that work in practice. Useful before scoping any agent POC.
A practical guide to building agents
OpenAI's guide to agent design, tools, guardrails and orchestration for deployment teams.
The Convergence of Presales and Post-Sales (Shamil Turner)
Figma's first Solutions/Sales Engineer on why presales is absorbing post-sales work and where the FDE role fits.
What an AI-Enabled SE Looks Like in 2026 (Darlene Volas)
Practical AI workflows for Solutions/Sales Engineering teams, from meeting prep automation to governance.
Debunking the Traditional Path to Presales (Adam Bauman)
A Kong staff Solutions/Sales Engineer on moving into presales and how to interview without prior Solutions/Sales Engineer experience.
Diary of a Sales Engineer
A podcast on Sales Engineer careers, including episodes on forward-deploy solution engineers and Field CTO paths.
Job postings for this tech role have grown more than 700%
Indeed data on how fast forward-deployed engineer postings grew from 2025 to 2026.
One of the fastest-growing jobs in Silicon Valley…
Lightcast data on FDE posting growth and median advertised pay.
What is a Forward Deployed Engineer? The fastest growing AI job
Labor-market analysis of US FDE posting volume from 2024 to 2026.

How Palantir built the ultimate founder factory | Nabeel S. Qureshi (founder, writer, ex-Palantir)
Lenny's Podcast · YouTube

The Production AI Playbook: Deploying Agents at Enterprise Scale — Sandipan Bhaumik, Databricks
AI Engineer · YouTube

Building Agents with Model Context Protocol - Full Workshop with Mahesh Murag of Anthropic
AI Engineer · YouTube

Why AI evals are the hottest new skill for product builders | Hamel Husain & Shreya Shankar
Lenny's Podcast · YouTube

AI Evaluations Clearly Explained in 50 Minutes (Real Example) | Hamel Husain
Peter Yang · YouTube

Solutions Architect Interview: Mock Discovery Call for Customer Needs (feat. Salesforce, Dropbox SA)
Aced (formerly Exponent) · YouTube

Solutions Architect Mock Interview - Product Demo of LabelBox and Databricks
Aced (formerly Exponent) · YouTube
sachin (@sachin_11004)
According to CNBC, Amazon Web Services and Anthropic are racing to build specialized AI engineering teams as Big Tech spends billions on artificial intelligence
Show details
According to CNBC, Amazon Web Services and Anthropic are racing to build specialized AI engineering teams as Big Tech spends billions on artificial intelligence and looks for proof that the investments can generate business results. AWS has committed $1 billion to a
Santhosh Patel (@santhosh_patell)
Anthropic just put $100M into Claude Frontier Academy (Oct 2) to train 10k Forward Deployed Engineers. And they are still hiring their own Claude Code + India A
Show details
Anthropic just put $100M into Claude Frontier Academy (Oct 2) to train 10k Forward Deployed Engineers. And they are still hiring their own Claude Code + India Applied AI seats hard. Open (Greenhouse, checked live): • Staff Software Engineer, Claude Code - SF / NYC / Seattle
Check your company's data policy first
Don't paste customer data, credentials or contracts into tools your company hasn't approved.
Show details
Don't paste customer data, credentials or contracts into tools your company hasn't approved.
Verify every number and claim
Treat model output as a draft. Check figures, product capabilities and competitor claims before they reach a customer.
Show details
Treat model output as a draft. Check figures, product capabilities and competitor claims before they reach a customer.
Use AI for demo data, not demo truth
Generate fake but realistic sample data; never let the model invent features your product doesn't have.
Show details
Generate fake but realistic sample data; never let the model invent features your product doesn't have.
Turn tribal knowledge into runbooks
Paste Slack threads and ask for numbered steps with verification and rollback. Then test the runbook once yourself.
Show details
Paste Slack threads and ask for numbered steps with verification and rollback. Then test the runbook once yourself.
Prep with a role-play
Ask the model to play the skeptical buyer or security reviewer and run through your demo or answers.
Show details
Ask the model to play the skeptical buyer or security reviewer and run through your demo or answers.
Learn how your tools connect to AI
Standards like the Model Context Protocol let assistants reach your tools and data; understanding them is quickly becoming part of deployment work.
Show details
Standards like the Model Context Protocol let assistants reach your tools and data; understanding them is quickly becoming part of deployment work.