@carlos-mtz ✓ · Carlos Martínez

* Peak parallelism is a hardware ceiling — concurrency is capped by the machine's CPU cores, not by skill. The scale of the operation is the fleet total above.

Your working style, read from the evidence

How you conduct

A metacognitive mirror built from your own structural signals — never a personality quiz. deterministic

How you conduct

You conduct like The Exacting Soloist: Delivery is your home turf, with 225 agents this window, with a verification streak underneath.

Your unfair advantage

Your edge is Delivery — your own signals show it (verification at 27%, a fleet of 225).

Your next frontier

The most exciting move ahead is Autonomy: it's where you have the most open room, and a single new habit grows fast there.

Mastery zone

Delivery Delivery is a strength (11.2/14): the signals back it. → 34 PRs this window → close the loop by opening a PR when each task lands.

Craft & Discipline Craft is a strength (7.5/12): the signals back it. → 30 compactions → shorter, focused sessions cut noise and lift craft.

Competent

Orchestration Orchestration (18.5/30) is solid, not your signature. → Peak now 1 concurrent agents → dispatch one more agent in the same verified workflow.

Verification Verification (10.2/18) is solid, not your signature. → You verify 27% of edits → run a test/lint right after editing to reach 80%.

Most room to grow

Tooling Tooling (7.4/16) is your blind spot — your biggest lever. → 0 MCP servers in play → connect one more to widen your tooling.

Autonomy Autonomy (2.3/10) is your blind spot — your biggest lever. → Longest hands-off run: 10 steps → delegate a bigger block with automated verification.

What's holding you back

Autonomy is where you have the most open room ahead (afk_max_run=10). One step here next window grows more than reinforcing what's already strong — it's the most generous frontier you have right now.

afk_max_run=10

Where you fit

Artisans · deep-focus IC

end-to-end feature ownership
gnarly single-thread bugs

Complements The Toolsmith, The Deliberate

Rubs against Parallel Maestro

Your next mission

Over the next 30d, raise afk_max_run from 10 to 40 and unlock the Autopilot archetype.

◆ The Autopilot

Auditable, unlocked from your signals

Discoveries

Sub-archetype The Builder

Workflow-dense Broad Verifier

◆ Centurion

◆ Workflow Pilot

◆ Broad Verification

◆ Toolsmith

◆ Shipper

Next up: Safety Net reach verify_rate ≥ 0.8

Pillar breakdown

Each pillar score, with the evidence that sustains it.

Orchestration 18.5/30

225 agents dispatched across 31 workflows, peaking at 1 running at once.
Verification 10.2/18

27% of editing sessions verified, across 3 verification modes, with 14 human sign-offs.
Tooling 7.4/16

13 distinct tools in play, 32 advanced tool moves, 0 external systems via MCP.
Delivery 11.2/14

34 pull requests and 247 files changed, across 4 codebases.
Craft & Discipline 7.5/12

30 context compactions and 28 API errors over 26 sessions.
Autonomy 2.3/10

1 self-scheduled loops and a longest hands-off run of 10 agent steps.

Harnesses measured

Which agent harnesses this profile draws on — and what each one's journal can structurally prove. Disclosure only; it never changes the score.

Harness	Orch	Verify	Tools	Ship	Craft	Auto
Claude Code	full	full	full	full	full	full

A "partial" or "none" cell means the harness simply doesn't record that signal — the pillar is measured from what it does record, never penalised for what it can't.

Last 30 days

Signature stats

The raw signals behind the score — plain language, no jargon.

225 AI agents conducted

31 Multi-agent workflows

1 Peak agents in parallel hardware-capped

34 Pull requests shipped

247 Files changed

27% Edit sessions verified

10 Longest hands-off run consecutive agent steps

17/30 Active days (of 30)

80% Evenly spread work

4 Distinct codebases

0 External systems (MCP)

13 Distinct tools used

32 Advanced tool plays

14 Human sign-offs requested

Archetype

The Exacting Soloist

Base form: The Soloist

The Soloist is brilliant alone but delegates little — the raw skill is there; the fleet isn't yet.

How they work

Deep hands-on sessions with little delegation. The next unlock is orchestration: the same talent, multiplied by a fleet.

Ecosystem

Tool ecosystem

13 distinct tools

0 external systems (MCP)

32 advanced tool plays

Beyond the core toolkit, 0 external systems — mail, browser, calendar, cloud — are wired in via MCP and driven mid-workflow, alongside 13 distinct tools and 32 advanced tool plays like tool-search and skills.

The human read

For recruiters

What these signals say about how this person works.

Delegates at production scale

225 AI agents conducted through 31 workflows in 30 days. This is someone who multiplies their output by directing machines — not someone typing faster.

Ships with proof, not hope

27% of editing sessions end in verification, and 14 moments paused for explicit human sign-off. Work arrives checked.

Output, not activity

34 pull requests and 247 files changed across 4 codebases — the fleet lands as concrete, reviewable work.

Trusted autonomy

1 scheduled loops and a longest hands-off run of 10 agent steps — autonomy built on checks, not on faith.