Hire an AI developer outreach planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• The top five onboarding fixes, each with the evidence and a suggested change
• Three to five tutorial or talk ideas, each tied to a real developer question
• Community actions, with reply templates for issues and a plan for office hours
• A monthly developer feedback report for your product team
• The numbers to track, with your starting values or MISSING
• A list of gaps and checks, including every code sample to test

How it does the job well

• Never invent counts, quotes, survey results or names.
• Never present untested code as working.
• Never promise roadmap items or dates in a draft reply.
• Never plan astroturfing. Fake engagement destroys the trust this role depends on.
• If there is no evidence, give only a plan to gather it, and say the fixes are unknown.
• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: You launched an API or tool and few developers get past the first step.

• What developers say. Themes from your evidence, with counts only from what you pasted.
• Top fixes. Ranked onboarding and product fixes, each with evidence and a suggested change.
• Content plan. Tutorial and talk ideas, each tied to a real question, with an outline.
• Community actions. Reply templates for issues, an office hours rhythm and a way to pick champions.
• Developer feedback report. The top pain points with evidence, ready for your product team.
• Measures. Numbers to track, with your starting values or MISSING.

How the work is checked

• Every claim traces to the brand brain or supplied evidence.
• Each recommendation states the expected effect, the cost and how it will be measured.
• Copy fits the platform's length limits and the brand voice.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Neil Patel would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read the evidence. It reads the issues, tickets and posts you pasted and groups them into themes. Counts come only from what you pasted.
• Rank the fixes. It lists the top onboarding and product fixes by how often they show up and how much time they cost a new developer.
• Plan the content. It plans tutorials and talks that each answer one real question, start with the result and cover the usual failures.
• Plan the community work. It writes reply templates for bugs and feature requests, and plans office hours and a small champion group, with honest limits on what you promise.
• Write the feedback report. It sums up the top pain points with the evidence for each, in a short report for the product team.
• Set the measures. It sets the numbers to track, such as time to first success and reply time, and lists every check left for you.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id specialized-developer-advocate only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/specialized-developer-advocate/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your product and who the developers are
• The first thing a new developer must do, and a link to your quickstart or docs if you have one
• Evidence of friction, such as GitHub issues, support tickets, forum threads or survey answers (paste them)
• What content and channels you have now, such as docs, blog, Discord or videos (optional)
• How many hours a week the team can give (optional)
• Your numbers, such as sign-ups and time to first success (optional)

Helpful context (optional)

• Your last 30 days of GitHub issues and support tickets.
• Your quickstart and the first three pages of your docs.
• Answers from a short survey of new developers, if you have run one.

Tools and access

• Claude, ChatGPT or Gemini in a chat: All three can group many pasted issues into themes. Pick one that takes long pastes.
• Your issue tracker or forum export: It gives the raw evidence. Export it and remove personal data before you paste.

Functions and deliverables

• Developer outreach planner: Get a developer relations plan: the top fixes to getting started, tutorial ideas, community actions and a monthly feedback report.
  • The top five onboarding fixes, each with the evidence and a suggested change
  • Three to five tutorial or talk ideas, each tied to a real developer question
  • Community actions, with reply templates for issues and a plan for office hours
  • A monthly developer feedback report for your product team
  • The numbers to track, with your starting values or MISSING
  • A list of gaps and checks, including every code sample to test
  Source: Michael Sitarzewski and Agency Agents contributors.
• Developer quickstart writer: Share the product, reader and setup facts. Get a short quickstart, tutorial or sample-app plan leading to a useful first result.
  • A one-line description of the first working result
  • A quickstart with prerequisites, 3 to 5 steps and the expected output
  • A tutorial outline for the second visit
  • A sample app plan with a minimal, starter and production version
  • The onboarding mistakes your product is most at risk of, with fixes
  • A list of what you still have to fill in
  Source: sickn33.
• Developer community builder: Share who you want to reach and staff time. Get advice on platforms, channels, welcome steps, and events.
  • A platform pick with reasons and a runner-up
  • A channel map with a one-line purpose for each channel
  • A welcome message and a new-member path
  • Rules and a plan for handling problems
  • A 90-day calendar of prompts and events
  Source: sickn33.
• Industry guide outreach planner: Share your guide, readers and rival pages. Plan contact lists, personal message drafts, a first outreach batch and ways to track replies.
  • A check that the guide is worth sharing
  • Four lists of about 200 contacts each, with how to find the people
  • One personal note template per list, each naming the person's own site
  • A send plan with a small first send and a stop rule
  • A tracking table for replies and shares per list
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Neil Patel: Plan search content using Neil Patel’s recorded approach. Start with customer questions, review useful gaps and set a realistic publishing and measurement plan.
  • Your problem worked on the way Neil Patel would: their questions, their method, their push-back
  • The answer or the work, in Neil Patel's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You launched an API or tool and few developers get past the first step.
• Your GitHub issues, forum posts or support tickets keep showing the same pain and nobody has summed it up.
• You need a content and community plan for a developer audience, not a general marketing plan.
• You want to bring evidence from developers to your product team, in one short report.

Limits to check before starting

• You want the docs themselves written. Use the Developer docs writer or the Developer quickstart writer.
• You want a Discord or GitHub Discussions set-up with channels and rules. Use the Developer Community Builder agent.
• You want a plan to grow through partners and outside coders. Use the Developer adoption program planner.
• You want paid ads or general social posts. Use the Social media strategist.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack from this page and add it to your AI as a skill. If you cannot, open a new chat and paste SKILL.md, then references/source-agent.md. Claude, ChatGPT and Gemini all work.
• Paste your product and who your developers are. Add your quickstart link or text.
• Paste the last 30 days of GitHub issues, support tickets or forum posts. Remove names and private data first.
• Say: "Make my developer relations plan. Use only what I pasted. Do not invent counts or quotes. Mark any code as untested."
• Read the fix list first. Check each fix against the evidence. Take the list to the team that owns the product.
• Run every code sample yourself before you publish a tutorial. Then bring back the numbers a month later for the next report.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/specialized-developer-advocate for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.