Part 1 The problemWhy teams need this
01 · THE PROBLEM
Consistent LinkedIn presence wins deals, and almost nobody sustains it because the research and drafting eat the time. This does the reading and the first draft in your voice, and leaves you the only part that matters: deciding what goes out under your name.
Part 2 How it worksWhat it does, step by step
02 · WHAT IT DOES
Twice a week it researches your topics from RSS sources and an AI search, saves the raw material and keeps what's relevant to your audience. For each story it picks a content pillar and drafts a post in your voice, then scores it. Drafts go to Slack. Reply approve and it's published; reply with feedback and it's rewritten and sent back.
03 · HOW IT RUNS
Step by step, as built.
Research twice a week
RSS sources and an AI search run in parallel and are merged.
Keep what's relevant
Raw content is saved and a classifier keeps only what matters to your audience.
Draft in your voice
A content pillar is chosen and Claude drafts the post from real examples of your writing, then scores it.
Review in Slack
Drafts arrive in Slack. You reply approve or give feedback.
Publish or rewrite
Approved posts publish to LinkedIn; feedback triggers a rewrite that comes back for another look.
04 · WHERE A PERSON STAYS IN
The machine drafts. A person decides.
Nothing is published without your approval in Slack. Feedback loops back into a rewrite, not a repost.
05 · TOOLS AND APPS
Built around the systems already in the process.
06 · WHEN SOMETHING BREAKS
Failure is designed in.
- 9nodes retry automatically when an external API fails.
- 2decision points (IF or Switch) check the data before it moves on.
- ✓Anything unhandled triggers our central error workflow, so a crash gets reported instead of failing silently.
Standard on every build
- Schema validation before downstream writes
- Retry and error routes for external API failures
- Duplicate-safe processing and idempotent updates
- Human approval where the action carries business risk
- Execution logging for support and audit review
Part 3 The impactWhat it's worth, and how we'd build yours
07 · PROJECTED IMPACT
What it should change in the business.
Projections for a typical deployment. The calculation below shows the math, and you can put in your own numbers.
08 · ROI CALCULATION
How it pays back in your business.
The starting numbers are a hypothetical deployment sized to the projections above. Change any of them to your own volumes and costs, and the math updates underneath.
- Full-time equivalent freed
- 0.1 people
- Gross value
- $4,608
- Running cost
- −$540
- Return per $1 of running cost
- $8.5
The math: 8 LinkedIn posts × 90 min × 12 months × 80% ÷ 60 = 115 hours a year × $40/hour = $4,608. Net value = gross value − $540 running cost a year.
09 · HOW WE'D BUILD YOURS
How we'd build yours.
- Discover: map the current process, systems, volumes, owners and exceptions.
- Design: define the canonical data model, approvals, retries and system boundaries.
- Build: implement credentials, nodes, validation and observable error routes.
- Prove: run controlled data through success, duplicate and failure scenarios.
- Operate: publish runbooks, ownership and measurable service levels.
