How you conduct
You conduct like The Instrument-Rated Pilot: Autonomy is your home turf, with 389 agents this window, with a verification streak underneath.
@gabi-ar ✓ · Gabriela Fontán
Flies blind with confidence because verification is your artificial horizon.
Practitioner
Maturity 58.5 · B- · Top 50%
Your blend
One score per tool
Your scores by harness
Each harness is scored only on what it can structurally observe (κ = observable capacity) and ranked against others on the same tool.
The fleet
389
AI agents conducted in the last 30 days
20
multi-agent workflows
1*
peak agents in parallel
18
work sessions
* 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
Your unfair advantage
Your edge is Autonomy — your own signals show it (verification at 28%, a fleet of 389).
Your next frontier
The most exciting move ahead is Delivery: it's where you have the most open room, and a single new habit grows fast there.
Mastery zone
Craft & Discipline
Craft is a strength (7.9/12): the signals back it.
→ 23 compactions → shorter, focused sessions cut noise and lift craft.
Autonomy
Autonomy is a strength (7.0/10): the signals back it.
→ Longest hands-off run: 63 steps → delegate a bigger block with automated verification.
Competent
Orchestration
Orchestration (18.7/30) is solid, not your signature.
→ Peak now 1 concurrent agents → dispatch one more agent in the same verified workflow.
Verification
Verification (11.5/18) is solid, not your signature.
→ You verify 28% of edits → run a test/lint right after editing to reach 80%.
Most room to grow
Tooling
Tooling (7.8/16) is your blind spot — your biggest lever.
→ 0 MCP servers in play → connect one more to widen your tooling.
Delivery
Delivery (5.6/14) is your blind spot — your biggest lever.
→ 4 PRs this window → close the loop by opening a PR when each task lands.
What's holding you back
Delivery is where you have the most open room ahead (prs=4). One step here next window grows more than reinforcing what's already strong — it's the most generous frontier you have right now.
prs=4
Where you fit
Orchestrators · autonomous IC on long tasks
- long hands-off builds
- overnight batch work
Complements The Deliberate, The Toolsmith
Rubs against The Soloist
Your next mission
Over the next 30d, raise prs from 4 to 7.
Auditable, unlocked from your signals
Discoveries
Sub-archetype
The Scheduler
AFK Marathoner
Workflow-dense
Broad Verifier
Centurion
Workflow Pilot
Broad Verification
Toolsmith
Hands-off
Self-scheduler
Pillar breakdown
Each pillar score, with the evidence that sustains it.
-
Orchestration 18.7/30
389 agents dispatched across 20 workflows, peaking at 1 running at once.
-
Verification 11.5/18
28% of editing sessions verified, across 4 verification modes, with 10 human sign-offs.
-
Tooling 7.8/16
14 distinct tools in play, 52 advanced tool moves, 0 external systems via MCP.
-
Delivery 5.6/14
4 pull requests and 53 files changed, across 4 codebases.
-
Craft & Discipline 7.9/12
23 context compactions and 9 API errors over 18 sessions.
-
Autonomy 7.0/10
41 self-scheduled loops and a longest hands-off run of 63 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.
389
AI agents conducted
20
Multi-agent workflows
1
Peak agents in parallel
hardware-capped
4
Pull requests shipped
53
Files changed
28%
Edit sessions verified
63
Longest hands-off run
consecutive agent steps
14/30
Active days (of 30)
82%
Evenly spread work
4
Distinct codebases
0
External systems (MCP)
14
Distinct tools used
52
Advanced tool plays
10
Human sign-offs requested
Archetype
The Instrument-Rated Pilot
Base form: The Autopilot
The Autopilot sets loops that keep working while they're away — and comes back to results, not surprises.
How they work
Work is framed as scheduled workflows with checkpoints: launch the fleet, step away, verify on return. Human attention goes only where it changes the outcome.
Ecosystem
Tool ecosystem
14
distinct tools
0
external systems (MCP)
52
advanced tool plays
Beyond the core toolkit, 0 external systems — mail, browser, calendar, cloud — are wired in via MCP and driven mid-workflow, alongside 14 distinct tools and 52 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
389 AI agents conducted through 20 workflows in 30 days. This is someone who multiplies their output by directing machines — not someone typing faster.
Ships with proof, not hope
28% of editing sessions end in verification, and 10 moments paused for explicit human sign-off. Work arrives checked.
Output, not activity
4 pull requests and 53 files changed across 4 codebases — the fleet lands as concrete, reviewable work.
Trusted autonomy
41 scheduled loops and a longest hands-off run of 63 agent steps — autonomy built on checks, not on faith.