From prompting to designing the flow.
What chains of steps look like.
How agents remember anything.
What an agent is allowed to touch.
Each box does one thing. The whole becomes the system.
If a step needs to know it tomorrow, store it today.
Daily notes. State files. Logs.
Gumloop carries values between nodes.
Notion pages. Sheets. SQL.
Anything you can do, the agent can do.
Read what comes in. Nothing else.
Why? Safety + cost + predictability.
One job per node. Easier to debug, easier to swap.
Glue with code. Reason with AI. You don't need an agent for everything.
Store state outside the prompt. Files, variables, databases.
At the moments that matter. Especially before something irreversible.
Folders are the system.
Vault/ ├─ CLAUDE.md ├─ Inbox.md ├─ Task Board.md ├─ Scratch Pad.md ├─ Daily Notes/ ├─ Agent Daily Notes/ ├─ Sessions/ └─ Research/
Twelve nodes. Three of them think.
Describe the flow. Gumloop builds it.
Build me an automated job hunting flow that does the following: • Search for jobs using a Google web search targeting site:boards.greenhouse.io for a specific role (e.g. "Forward Deployed Engineer" or "Forward Deployment Engineer") • Scrape a specific company's job board (e.g. Anthropic's Greenhouse page at boards.greenhouse.io/anthropic) to get their latest listings • Combine both job sources into unified parallel lists of: job URLs, job descriptions, company names, and job titles • Read my resume from a Google Doc link I provide • Score each job using AI — compare my resume against every job description and generate a match score from 1–10 with a 1-2 sentence justification • Filter jobs that score below a minimum threshold (e.g. 7 out of 10) • Tailor my resume for each qualifying job using AI — rewrite it to mirror the job's language and highlight the most relevant experience, without inventing anything • Save each tailored resume as a separate Google Doc • Log all results into a Google Sheets job tracker with these columns: Title, Company, Job URL, Score, Justification, Resume Link
Watch for three things.