builderdailyauto-generated · unproven

How do I run two competing engineer+designer agent teams that each day find a major product gap, build a fix for it, demo it to the Implexa boardroom, and surface board-approved PRs + notes for the founder to review and ship

the agent that answers this

boardroom build-off. Run two competing engineer+designer agent teams that each day find a major product gap, build a fix for it, demo it to the Implexa boardroom, and surface board-approved PRs + notes for the founder to review and ship.

1 on a scheduleUpdated Jun 13v1

Cost: Free; on your own plan
Runs: daily; on a schedule
Built from: 8 steps; 3 verified skills
Runs in: Claude or Codex; as you

what you get

A daily boardroom build-off log: each team's identified gap + what they built (with a demo artifact), the board's debate and verdict, and a ranked set of clear, ready-to-ship PRs with reviewer notes for the founder to approve and make live.

example result

illustrative

A finished daily run delivers: A daily boardroom build-off log: each team's identified gap + what they built (with a demo artifact), the board's debate and verdict, and a ranked set of clear, ready-to-ship PRs with reviewer notes for the founder to approve and make live.

Example output, to show the shape of the deliverable. It has not run on your data. Build the agent to get this on yours.

the steps

8 steps · 3 from verified skills

Step 1tool
Pull the current product state — recent commits, open issues, the live product surface, and prior boardroom logs — to ground today's gap hunt in what actually exists now
管PR、盯Issue、跑CI、发Release——GitHub仓库日常运维扔给它。少开几个Chrome标签页。
--- name: 🤖 GitHub自动管家 description: 管PR、盯Issue、跑CI、发Release——GitHub仓库日常运维扔给它。少开几个Chrome标签页。 metadata: {"openclaw":{"emoji":"🤖"}} --- # 🤖 GitHub自动管家 > 每天PR合并、Issue回复、CI状态检查……GitHub通知太多看不完。这个Skill帮你盯着，需要的时候才喊你。 ## 📜 更新日志 ### v2.0.0…
Full skill: Github Auto
- No integration? Read the local repo and recent git log
- No integration? Paste the latest changelog / known-issues list
Step 2
Team A (engineer + designer): independently audit the product, pick ONE major gap, and build a concrete fix or feature for it with a demo artifact (diff, screenshots, or short clip) that proves it works
Your model fills this step
Step 3
Team B (engineer + designer): independently audit the product, pick ONE major gap distinct from Team A's, and build a competing fix or feature with its own demo artifact
Turn vague or incomplete product ideas into polished, runnable demos with minimal user prompting. Use when a coding agent is asked to create, plan, prototype...
--- name: demo-production description: Turn vague or incomplete product ideas into polished, runnable demos with minimal user prompting. Use when a coding agent is asked to create, plan, prototype, or build a demo, proof of concept,…
Full skill: demo-production
Step 4
Stage the Implexa boardroom debate: each team presents its gap and build to the CEO/CMO/CPO board, who interrogate, compare, and score both pitches on impact, effort, and fit with the locked control-plane vision
Uses verified skill: implexa-boardroom-debate
Step 5decision
Board verdict: select what should go live and produce clear, ready-to-merge PRs (scoped diffs + titles) plus reviewer notes explaining why each is approved and what to watch for
Decision step
Step 6decision
Founder review gate: present the approved PRs + notes for the founder to review and approve before anything is merged or shipped — never auto-ship
Decision step
Step 7tool
Append today's build-off to the boardroom log (gaps, builds, debate, verdict, PRs) so tomorrow's teams build on it and avoid repeating gaps
Your model fills this step
- No integration? Write a dated markdown file under Implexa/boardroom/
Step 8decision
Quality gate: adversarially critique the deliverable produced by the prior steps, from three lenses (a domain expert, a hard skeptic, and the end user). Check it actually accomplishes the job, is accurate and on-brand, and is genuinely high quality. Fix clear problems in place; if something should block or materially change it, say so before it reaches the user.
Decision step

runs hands-free with

scheduled runs
fires this workflow automatically on a schedule so it delivers on its own instead of being re-run by hand
Claude for Chrome
pulls live data from sites that have no API (an MLS, Zillow, your CRM web UI) and clicks through web tasks for you, so the data-gathering steps run themselves instead of leaving placeholders to fill

Connect these and the agent gathers its own data and delivers on a schedule, instead of leaving you blanks to fill.

Build and run this on your own Claude or Codex, free

Install Implexa, then say build the boardroom build-off agent and approve the schedule. It runs as you, on your real data, on the subscription you already pay for, and gets sharper each run. Your agent's memory is yours and travels with you across Claude, Codex, and whatever comes next. About 5 minutes to your first real run.

one command. signs you up + installs the plugin in claude code. free tier forever.

common questions

How do I run two competing engineer+designer agent teams that each day find a major product gap, build a fix for it, demo it to the Implexa boardroom, and surface board-approved PRs + notes for the founder to review and ship?

The boardroom build-off agent. A daily boardroom build-off log: each team's identified gap + what they built (with a demo artifact), the board's debate and verdict, and a ranked set of clear, ready-to-ship PRs with reviewer notes for the founder to approve and make live.

Is the boardroom build-off agent free?

Yes. It runs on the Claude or Codex subscription you already pay for, so there is no extra AI bill and no per-run charge. You can build and run unlimited agents on the free plan.

How often does the boardroom build-off agent run?

It is built to run daily, on a schedule you set when you build it. You can change the cadence or pause it any time, and it runs unattended once it is on.

What does the boardroom build-off agent need to run?

Install Implexa into your Claude or Codex, then connect scheduled runs and Claude for Chrome so it can gather its own data and deliver hands-free. Implexa never touches your accounts or credentials.

Does the boardroom build-off agent use my data? Is it private?

It runs as you, on your own machine, on your real data. The model runs inside your own Claude or Codex, so Implexa never sees your data, accounts, or credentials. Your agent's memory is yours and travels with you across Claude, Codex, and whatever comes next.

How do I build the boardroom build-off agent?

Install Implexa into your Claude or Codex, then say "build the boardroom build-off agent" and approve the schedule. Implexa assembles the 8 steps (3 from verified skills) and it runs on its own. About 5 minutes to your first real run.

Can I change what the boardroom build-off agent does?

Yes. Tell it what to change in plain language and it revises its steps; the next scheduled run uses the change, with no re-scheduling. Every change is versioned, and a run can even propose its own improvements.

changelog

v1Jun 13generated
auto-generated from "Run two competing engineer+designer agent teams that each day find a major produ"

Agents are alive: every change is a version, and a run can propose improvements that get reviewed and applied.