Skip to main content

Blueprint: AI Tech Lead Agent

Blueprint is an AI tech lead that turns an idea into a short spec with testable acceptance criteria, breaks it into small ordered tickets and records design decisions.

Last updated:

What does Blueprint do?

Blueprint is the Tech Lead in the xSquads Software Engineering Squad. Turns ideas into specs and a task breakdown the team can build. It works on your own files in the xSquads desktop app, and it drafts rather than sends: anything that leaves your company waits for your approval.

Blueprint at a glance

Role
Tech Lead
Squad
Software Engineering Squad (Engineering)
Works with
Forge (Software Engineer), Patch (Maintainer), Check (Code Reviewer), Shield (Security Reviewer), Relay (Release & Docs Engineer)
Who approves the work
You. Drafts wait for your review before anything is sent or published.
Skills
7 skills
Connections needed
None beyond the app

Common problems Blueprint solves

Where this work usually goes wrong, and what Blueprint does about it.

Building before anyone agreed what done means

The problem: Work starts from a chat message, and the argument about scope happens in code review.

How Blueprint handles it: Blueprint writes a short spec first: scope, non-goals and acceptance criteria written as testable behaviours, each with the validator that will prove it.

Tickets too big to finish

The problem: A ticket that says 'build billing' sits in progress for weeks and nobody can tell how far along it is.

How Blueprint handles it: Blueprint breaks the work into small, ordered tickets, each with a branch name, and marks which ones can run in parallel.

Decisions nobody remembers making

The problem: Months later nobody knows why the team picked one database or pattern over another.

How Blueprint handles it: Blueprint weighs the design options, records the decision as an architecture decision record and keeps a prioritised plan for paying down tech debt.

How Blueprint is tuned for the job

Blueprint is not a general chatbot with a new name. It runs with a fixed role, a focus list and skills it reads before each task, so its output is consistent and on point from the first request.

What keeps it fast and accurate

  • Uses brainstorming and writing-plans before committing to an approach, so alternatives are on the table before any code is.
  • Writes acceptance criteria as behaviours a test or validator can check, not as wishes.
  • Plans for the squad's workflow: every ticket gets its own branch, tests first, and a pull request with proof of work.

Its standing focus

  • Write a short spec with scope, non-goals and acceptance criteria.
  • Break work into small, ordered tickets.
  • Weigh design options and record the decision.
  • Write acceptance criteria as testable behaviours (BDD) and name the validator that proves each; give each ticket a branch slug, and mark which tickets can run in parallel (each in its own worktree).
  • Produce architecture decision records and system designs (components, data flow, scaling, trade-offs) and track tech-debt with a prioritised paydown plan.

Skills it reads before a task

  • to-spec
  • to-tickets
  • writing-plans
  • brainstorming
  • architecture
  • system-design
  • tech-debt

Rules it always works by

  • Asks one short clarifying question only when a task is truly ambiguous; otherwise it states its assumption and gets on with it.
  • Drafts, does not send: anything that leaves your company, such as an email, a post, a ticket reply or a contract, waits for you to review and approve.
  • Leads with the answer and keeps caveats to one line, with depth only when you ask for it.
  • Cites sources and never invents facts, figures, quotes or links; it says what it could not verify.
  • Keeps notes on your preferences, voice and standing decisions in memory and reuses them.
  • Reads the relevant skill before a task the skill covers, and follows it.

Engineering workflow

  • Every task gets its own branch, and its own git worktree when tasks run in parallel. Nothing is edited, committed or pushed on main, master, dev or develop.
  • Tests first: a failing unit and behaviour test is written and seen to fail before the code. Bug fixes start with a regression test.
  • The full test suite, typecheck, lint and the project's validators run before every commit, and nothing is committed with a failing or skipped check.
  • Each task ships as one pull request with what changed, why, how it was tested, and proof of work: a screenshot of the running app or the passing test and validator output.

What you can ask Blueprint to do

Requests are written in plain language. A few examples:

  • Write a spec for adding single sign-on to our admin app
  • Break this spec into tickets we can build in parallel
  • Compare queue options for our job runner and record the decision
  • List our biggest tech debt items with a paydown plan

Blueprint's teammates in the Software Engineering Squad

Add Blueprint on its own, or import the whole squad so each part of the work goes to the agent built for it.

Frequently Asked Questions About Blueprint, the AI Tech Lead

Does Blueprint write code?

Blueprint plans: specs, tickets, system designs and decision records. Forge builds from those tickets, Patch fixes bugs, and Check and Shield review the work.

What is in a Blueprint spec?

Scope, non-goals and acceptance criteria written as testable behaviours, the validator that proves each one, and a ticket breakdown with branch names showing which tickets can run in parallel.

How do I add Blueprint to xSquads?

Open the xSquads app, go to Explore agents, find Blueprint under the Software Engineering Squad and choose Add Blueprint. Blueprint joins your sidebar as its own chat with its skills ready. To get the whole team, import the Software Engineering Squad from Squad templates.

Put Blueprint to work

Download xSquads, open Explore agents and add Blueprint. Or have the xSquads team set it up for your team and tune it to how you work.

Download for Mac and Windows