The agent flow behind the briefing.
A 7-stage pipeline from raw signal sources to LinkedIn publish — with the LinkedIn Post Generator engineered as Fan-Out + Reflection to solve the hook problem. This is what a PM-led agent design looks like end to end.
The 7-stage pipeline
Click any stage to expand its input/output, design notes, failure modes, and the checkpoints generated there. The pain point is auto-opened.
Where N parallel generators run with distinct strategies — diversity, not redundancy.
Where a critic agent scores output against a rubric and triggers regeneration if it falls short.
Where a typed input/output schema (and rubric) gates what passes between stages.
Newsletters, RSS feeds, Twitter/X lists, Slack channels — wherever signal-worthy AI PM news surfaces.
Reads raw inputs, identifies items that qualify as AI PM signals, and scores relevance.
Removes signals published in prior editions, formats survivors in the 📌 numbered style.
Generates 3 variants with different hook angles, critic scores each against a rubric, surfaces the best to human.
- ·All 3 variants using the same hook angle
- ·Generic hook ("AI is changing things")
- ·Critic missing real tone problems while nitpicking style
Generates 3 variants with different hook angles, critic scores each against a rubric, surfaces the best to human.
This is the stage that gets the full Post Generator Contract — input/output schema, weighted critic rubric, failure modes. See the Contract tab.
3 parallel generators run with predefined hook strategies (surprising claim · trend read · contrarian take). One inference call per variant.
Critic agent scores each variant against the rubric (Hook 30% · Voice 25% · Signal 20% · Format 15% · CTA 10%). Below 7.5 weighted → regenerate.
- ·All 3 variants using the same hook angle
- ·Generic hook ("AI is changing things")
- ·Critic missing real tone problems while nitpicking style
Rahul picks the preferred variant — or approves the auto-selected top-scorer if score ≥ 8.0.
Applies any selection edits, finalises spacing, emoji, and CTA. One lightweight reflect pass.
One-click final approval. Posts to LinkedIn via API or clipboard. Logs to edition archive.