implexa
All agents
creatordaily

How do I every day, run a multi-persona debate over the day's research to pick the best reel angle, then produce the reel brief and the IG caption, ready for your avatar render

the agent that answers this

Daily IG reel: debate and brief. Every day, run a multi-persona debate over the day's research to pick the best reel angle, then produce the reel brief and the IG caption, ready for your avatar render.

4 runsLast run 23d agoUpdated Jun 6v10
Cost
Free
on your own plan
Runs
daily
on a schedule
Built from
12 steps
6 verified skills
Runs in
Claude or Codex
as you

what you get

a reel brief with avatar script and visual schedule plus a paste-ready IG caption, approved before production

example result

illustrative

A finished daily run delivers: a reel brief with avatar script and visual schedule plus a paste-ready IG caption, approved before production

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

improved recently

v10Jun 5

Added the companion-guide step: every reel must also write + publish the day-N guide at implexa.ai/guides/day-N (same structure as the existing guides, drawn from the brief) and put that guide link in the reel's pinned IG comment. This lapsed after day-2; now it's a required step so it happens daily without fail.

why: a run flagged its own gap and the fix was applied

Agents are alive: a run can catch its own gaps and propose a fix. This is real run history, not a directory listing.

the steps

12 steps · 6 from verified skills

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.

Run this agent in Implexa, on your own Claude or Codex, free

Get the Implexa app (or connect your Claude Code / Codex), then say build the Daily IG reel: debate and brief 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.

Run this agent in Implexa →

common questions

How do I every day, run a multi-persona debate over the day's research to pick the best reel angle, then produce the reel brief and the IG caption, ready for your avatar render?

The Daily IG reel: debate and brief agent. a reel brief with avatar script and visual schedule plus a paste-ready IG caption, approved before production

Is the Daily IG reel: debate and brief 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 Daily IG reel: debate and brief 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 Daily IG reel: debate and brief 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 Daily IG reel: debate and brief 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 Daily IG reel: debate and brief agent?

Install Implexa into your Claude or Codex, then say "build the Daily IG reel: debate and brief agent" and approve the schedule. Implexa assembles the 12 steps (6 from verified skills) and it runs on its own. About 5 minutes to your first real run.

Can I change what the Daily IG reel: debate and brief 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

  1. v10Jun 5feedback

    Added the companion-guide step: every reel must also write + publish the day-N guide at implexa.ai/guides/day-N (same structure as the existing guides, drawn from the brief) and put that guide link in the reel's pinned IG comment. This lapsed after day-2; now it's a required step so it happens daily without fail.

  2. v9Jun 5feedback

    Made the upstream steps cost-aware: HeyGen regeneration is expensive, so the debate + brief + approval steps must lock a first-time-right avatar script (no letter-by-letter D.M./U.R.L., the Claude Code/Codex 'build by a prompt' must-say, smooth spoken seams, pronunciation respellings) BEFORE any render. Debaters now pressure-test the script for AI-tells + content gaps.

  3. v8Jun 5feedback

    Added a top-1%-editor 'reel-editor-critique' QC gate as the final step: reviews the finished reel AND its script for AI-tells (letter-by-letter D.M./U.R.L. reads), awkward spoken seams, pacing, caption/overlay issues, and content gaps (e.g. failing to say you can build/deploy with a prompt in Claude Code/Codex). HOLD/RESHOOT loops back to a re-render.

  4. v7Jun 4feedback

    Added a Chrome-MCP "capture real app surfaces → rebuild as on-brand Remotion components" step (skill: app-ui-capture-to-remotion) after HeyGen, so reels show the actual stack (Vercel/Claude/Supabase/Stripe) in motion instead of generic talking-head + text.

  5. v6Jun 4feedback

    fixed step 1: load the research workflow's bundle instead of the IG DM monitor

  6. v5Jun 4feedback

    swapped the reel debate step to the LLM Council (5-persona) skill; kept red-team as the critique gate

  7. v4Jun 4feedback

    caption humanizer step, restoring the original step bindings the auto re-bind dropped

  8. v3Jun 4manual

    added 1 step; rebound step 4 (clawhub/veezvg-episode-to-instagram -> gap), step 5 (decision -> skills.sh/humanizer), step 6 (unbound -> decision), and more

  9. v2Jun 4feedback

    Added a Claude-for-Chrome HeyGen avatar-render step from the approved brief, plus an adversarial critique gate that stress-tests the full package before the final Runway/Remotion render.

  10. v1Jun 3generated

    auto-generated from "Every day, run a multi-persona debate over the research bundle to pick the best "

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

related agents