How you conduct
You conduct like The Tempered Conductor: Orchestration is your home turf, with 4766 agents this window, with a verification streak underneath.
@devi-raman ✓ · Devika Raman
Conducts many at once — and lets none pass without proving it's clean.
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
4,766
AI agents conducted in the last 30 days
441
multi-agent workflows
6*
peak agents in parallel
36
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 Orchestration — your own signals show it (verification at 28%, a fleet of 4766).
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
Orchestration
Orchestration is a strength (27.3/30): the signals back it.
→ Peak now 6 concurrent agents → dispatch one more agent in the same verified workflow.
Craft & Discipline
Craft is a strength (9.0/12): the signals back it.
→ 47 compactions → shorter, focused sessions cut noise and lift craft.
Competent
Verification
Verification (12.2/18) is solid, not your signature.
→ You verify 28% of edits → run a test/lint right after editing to reach 80%.
Tooling
Tooling (8.9/16) is solid, not your signature.
→ 0 MCP servers in play → connect one more to widen your tooling.
Most room to grow
Delivery
Delivery (7.6/14) is your blind spot — your biggest lever.
→ 8 PRs this window → close the loop by opening a PR when each task lands.
Autonomy
Autonomy (3.2/10) is your blind spot — your biggest lever.
→ Longest hands-off run: 11 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=11). 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=11
Where you fit
Orchestrators · fleet tech lead
- large parallelizable migrations
- multi-front delivery
Complements The Toolsmith, The Deliberate
Rubs against The Soloist
Your next mission
Over the next 30d, raise afk_max_run from 11 to 40 and unlock the Autopilot archetype.
The Autopilot
Auditable, unlocked from your signals
Discoveries
Sub-archetype
Fleet Maestro
Heavy Fleet
Workflow-dense
Tool Scout
Broad Verifier
Parallel Trio
Swarm
Centurion
Legion Commander
Workflow Pilot
Broad Verification
Toolsmith
Shipper
Pillar breakdown
Each pillar score, with the evidence that sustains it.
-
Orchestration 27.3/30
4,766 agents dispatched across 441 workflows, peaking at 6 running at once.
-
Verification 12.2/18
28% of editing sessions verified, across 4 verification modes, with 23 human sign-offs.
-
Tooling 8.9/16
15 distinct tools in play, 97 advanced tool moves, 0 external systems via MCP.
-
Delivery 7.6/14
8 pull requests and 126 files changed, across 4 codebases.
-
Craft & Discipline 9.0/12
47 context compactions and 19 API errors over 36 sessions.
-
Autonomy 3.2/10
2 self-scheduled loops and a longest hands-off run of 11 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.
4,766
AI agents conducted
441
Multi-agent workflows
6
Peak agents in parallel
hardware-capped
8
Pull requests shipped
126
Files changed
28%
Edit sessions verified
11
Longest hands-off run
consecutive agent steps
22/30
Active days (of 30)
80%
Evenly spread work
4
Distinct codebases
0
External systems (MCP)
15
Distinct tools used
97
Advanced tool plays
23
Human sign-offs requested
Archetype
The Tempered Conductor
Base form: Parallel Maestro
The Parallel Maestro runs many agents at once and keeps them coherent — many hands, one baton.
How they work
Work is split into concurrent lanes: agents fan out in parallel, each with a clear mandate, and results converge into one deliverable. Coordination is the craft.
Ecosystem
Tool ecosystem
15
distinct tools
0
external systems (MCP)
97
advanced tool plays
Beyond the core toolkit, 0 external systems — mail, browser, calendar, cloud — are wired in via MCP and driven mid-workflow, alongside 15 distinct tools and 97 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
4,766 AI agents conducted through 441 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 23 moments paused for explicit human sign-off. Work arrives checked.
Output, not activity
8 pull requests and 126 files changed across 4 codebases — the fleet lands as concrete, reviewable work.
Trusted autonomy
2 scheduled loops and a longest hands-off run of 11 agent steps — autonomy built on checks, not on faith.