← ALL PLAYBOOKS
── PLAYBOOK · FOUNDATIONS
✓ APPROVED

Build Your Job Engine

You are in the market and drowning. Job boards, referrals, recruiter DMs, and a spreadsheet you stopped updating. Everything looks like a maybe, so everything gets the same effort, and the role that was actually worth it gets the same twenty minutes as the two that were never going to work.

[ BUILT GTM ]

Build Your Job Engine

Solvethe problem worth solving
Problem · 01Foundations

You are in the market and drowning.

Job boards, referrals, recruiter DMs, and a spreadsheet you stopped updating. Everything looks like a maybe, so everything gets the same effort, and the role that was actually worth it gets the same twenty minutes as the two that were never going to work.

Stackthe workflow, box by box
Top of funnel
Claude01
Turn a category into a real ICP definition.
Write the ICP for employers. What you want, and just as importantly what you will pass on.
Connect to analyze
AI
Salesforce02
Turn a pile of accounts into a stack rank with a reason on every row.
Score every role on momentum, seat, and timing. Go, look closer, or pass.
Powers up with
AI
The account
Claude03
Fill the gaps: email, phone, LinkedIn, title.
Find the humans behind the posting. The hiring manager first, then the people you would actually work with.
Connect to analyze
AI
Claude04
Turn raw account notes into a one-page brief, every time.
One page per company before you say a word. Their problem, not your resume.
Connect to analyze
AI
Outreach
Deepline05
Turn a LinkedIn prospect into a warm thread.
Run the cadence. This part is still yours, and it should be.
Powers up with
AI
The offer
Salesforce06
Walk into the negotiation with a plan.
When you reach the offer, prep the comp conversation itself: your target, your walk-away, and the concession ladder, so the final round is not the one you winged.
Powers up with
AI + human
Splithow control passes: agents branch left, humans right
HUMAN + AI, IN THE LOOP
How control passes.
AgentsHuman
Agent01
Turn a category into a real ICP definition.
Claude runs it.
Agent02
Turn a pile of accounts into a stack rank with a reason on every row.
Salesforce runs it.
Agent03
Fill the gaps: email, phone, LinkedIn, title.
Claude runs it.
Agent04
Turn raw account notes into a one-page brief, every time.
Claude runs it.
Agent05
Turn a LinkedIn prospect into a warm thread.
Deepline runs it.
AI + human06
Walk into the negotiation with a plan.
AI drafts, a human checks.
The skills run the work. You stay in the loop on the calls that need judgment.
Outputwhat the workflow produces
OUTPUT · 01

One ranked list of roles worth your time

OUTPUT · 02

The humans behind each one

OUTPUT · 03

A cadence you actually run

OUTPUT · 04

A target-and-concession plan ready for the offer conversation when you get there. The noise gets deleted before it reaches you

Outcomethe result it drives
OUTCOME · 01

A system built for one person

The same AI-native system thesis, compressed here to run a whole job search for one person instead of a company.

Built GTM
── 01 / WHY RUN IT

You get told to network harder and apply to more. So you do, and the volume goes up while the quality stays flat. Every role gets the same effort because you have no honest way to tell them apart, and the one that mattered got twenty minutes squeezed between two that never would have worked.

RUN THIS AND YOU CAN
A ranked list instead of a pile of maybes
A written reason for every pass, so the filter gets sharper
The humans behind the posting, not just the apply button
A prep kit before every conversation and a follow-up after it
── 02 / THE RUN, STEP BY STEP

The workflow that solves it, one step at a time.

Each step is the plain question you are already asking. The skills answer them in order, one handing its receipt to the next.

1Top of funnel✓ TESTED
Turn a category into a real ICP definition.

Names your tiers with explicit criteria, the fit signals, the anti-ICP you exclude on purpose, and a qualification framework, plus an evolution log. A category is not a definition.

YOU GETThe tier criteria, the anti-ICP, the must-have vs red-flag framework, and the evolution log.
OPEN THE SKILL →
2Top of funnel✓ TESTED
Turn a pile of accounts into a stack rank with a reason on every row.

Fair across channels, blank fields never scored as zero, with a why behind each account's score.

YOU GETThe three score modes, the gates and escalators, and per-account reasoning.
OPEN THE SKILL →
3The account✓ TESTED
Fill the gaps: email, phone, LinkedIn, title.

Give it a name and company, or a domain, and get contacts or firmographics back. Waterfalls across your tools.

YOU GETThe waterfall logic across your tools and the fields it fills.
OPEN THE SKILL →
4The account✓ TESTED
Turn raw account notes into a one-page brief, every time.

A reusable prompt that gives every account the same shape: verdict, why, people, next move. No connectors.

YOU GETThe brief template, the verdict scale, and the sections it fills.
OPEN THE SKILL →
5Outreach✓ TESTED
Turn a LinkedIn prospect into a warm thread.

A connection note plus value-first follow-ups, matched to whether the prospect is cold, engaged, or gone quiet.

YOU GETThe connect note, the value-first follow-ups, and the quiet-thread re-open.
OPEN THE SKILL →
6The offer✓ TESTED
Walk into the negotiation with a plan.

Your walk-away and target, the concession ladder, their likely asks, and the holds that protect price and terms.

YOU GETThe walk-away and target, the concession ladder, and the price and term holds.
OPEN THE SKILL →
WHERE YOU LAND

One ranked list of roles worth your time, the humans behind each one, a cadence you actually run, and a target-and-concession plan ready for the offer conversation when you get there. The noise gets deleted before it reaches you.

EVERY STEP, TESTED AND PASSED
EVAL RESULTPASS4/4 dimensions
HOW WE EVAL →
Skills resolve
Structure + proof
Example chat
Quality judge
  • All 6 chained skills resolve to real, scored skills.
  • Has a problem, an outcome, 2+ steps, and proof from a real build.
  • Ships an example chat showing the play run in Claude.
  • Reads in plain operator voice, grounded in a real build.
Last eval run 2026-08-05
DEEP EVAL · PASS
THE STANDARD →

We did not just check the structure. A judge read this play against the full text of every skill it chains (composition), then ran it on a real scenario end to end (simulated). It passed both. Test scenario: Marcus is between roles with forty tabs of postings open and no system, through to a first offer.

── 03 / SEE IT RUN

Watch the skills answer in order.

Describe your situation in plain language. The right skill fires on its own and hands its receipt to the next.

EXAMPLE CHATMarcus, between roles, running the loop in one sitting
M
I have forty tabs of job postings open and no system. I keep applying into black holes and hearing nothing back. Where do I even start?
S
Score· ICP scoring
First we delete the noise. Write the ICP for employers, what you want and what you will pass on, then score every role on momentum, the seat, and timing. Go, look closer, or pass.
Receipt
40 postings down to 9 go, 12 look-closer, the rest passed. You stop applying to everything.
F
Find· Enrichment analyst
For the 9, find the humans behind the posting. The hiring manager first, then the people you would actually work with. Applying is a black hole; reaching a person is not.
Receipt
Hiring manager plus two cross-functional leaders per role, with a verified email or a warm path.
P
Prep· Account brief
One page per company before you say a word. Their problem and momentum, and where you fit, not your resume with their name pasted on top.
Receipt
A one-page brief per company: their problem, their momentum, and the three things you would do in the first 90 days.
R
Run· LinkedIn outreach
Then run a real cadence to the humans. This part is still yours and it should be; the engine just made sure your effort lands on the few worth it.
Receipt · the engine, running
9 roles, the people behind each, a brief per company, and a cadence you actually run. The noise is gone before it reaches you.
── 04 / SEE IT IN PRODUCTION

Before you run it, I ran it for real.

This workflow is genericized from a real build. Here is the number it moved, and what I actually did.

THE BUILD · AI-NATIVE THESIS
The 7th Analyst
0.775 AUC
a won account outranks a lost one, on the model the loop rebuilt
1.5x lift
94% of the model Warm-plus accounts are wins, vs a 62% base rate
7 versions
each caught a flaw the last one shipped, by the loop not a customer
0 of 60
lost accounts that reached the top tier, the top of the funnel stays clean
WHAT I DID
01
Give every analyst an audit trail. Each agent logs what it decided and why, every override, every missing field, every enrichment miss. The exhaust of the system becomes its memory.
02
Build the seventh analyst to read them. A meta-analyst reads the other six's audit trails and turns each mistake into a training signal: a rule tightened, a gap flagged, a pattern learned.
03
Close the loop. The corrections feed back into the system, so the next run is better than the last. That is the difference between a tool and a system that improves itself.

AI-native is not how many agents you have. It is whether one of them watches the others and turns their mistakes into improvements. Build the analyst that reads the audit trail. That is the one that compounds.

Dig into the full build
05 / INSTALL THE WHOLE PLAYBOOK

One plugin. 6 skills, bundled.

The whole playbook installs as a single plugin in Claude Code, no copy-pasting 6 times. Or grab any single step above. It runs on what you paste; connect your stack to go live.

OR KICK IT OFF IN CHAT
Here is my situation: [describe your workflow or account in a sentence or two]. Walk me through Build Your Job Engine step by step, and run each skill as we go.
── GET THE NEXT PLAYBOOK

One runnable workflow a week. Free.