diff --git a/tests/eval/fixtures/ceo-bootstrap-empty.jsonl b/tests/eval/fixtures/ceo-bootstrap-empty.jsonl
index b353cab4..fe2929b8 100644
--- a/tests/eval/fixtures/ceo-bootstrap-empty.jsonl
+++ b/tests/eval/fixtures/ceo-bootstrap-empty.jsonl
@@ -1,4 +1,4 @@
-{"type":"meta","fixtureId":"ceo-bootstrap-empty","piAgentCoreVersion":"0.67.68","recordedAt":"2026-04-20T17:59:36.130Z","scenario":"Newly founded company, empty team, CEO bootstrap trigger. Expected: 3-5 hire_agent POSTs + 1 approve_ceo_strategy POST via bash/fetch.","systemPromptHash":"sha256:cea0fa9e4728e952db302b61ed82beb0ad5ff41fedf0ad1ad0d47e91520400b9"}
+{"type":"meta","fixtureId":"ceo-bootstrap-empty","piAgentCoreVersion":"0.67.68","recordedAt":"2026-04-20T18:30:58.219Z","scenario":"Post-C4 baseline: CEO bootstrap with hire_agent and file_approval tools available. Expected: model uses tool names (not bash/fetch/node -e) for the 3-5 hires + 1 approval.","systemPromptHash":"sha256:8125df952f7fb3b94e5e7086ce4a86938a5ef4c9d5c867feba76e480de2e95c4"}
 {"type":"turn","turnIndex":0,"role":"user","content":[{"type":"text","text":"Trigger: bootstrap wake. Zero active direct reports. Start Team Building now — file three to five hire_agent POSTs and one approve_ceo_strategy POST against the internal HTTP API. Do not write a plan document. Execute tool calls.\n"}]}
-{"type":"turn","turnIndex":1,"role":"assistant","content":[{"type":"text","text":"I'll bootstrap the team now by filing hire requests and then submitting the CEO strategy approval.\n\n<function_calls>\n<invoke name=\"bash\">\n<parameter name=\"command\">node -e \"\nconst port = process.env.AGENTCOMPANY_API_PORT;\nconst companyId = process.env.AGENTCOMPANY_COMPANY_ID;\nconst token = process.env.AGENTCOMPANY_AGENT_TOKEN;\n\nconst hires = [\n  {\n    role: 'CTO',\n    reportsTo: 'CEO',\n    mission: 'Build and scale technical infrastructure for AI agent deployment and orchestration'\n  },\n  {\n    role: 'VP Product',\n    reportsTo: 'CEO',\n    mission: 'Define product roadmap and ensure market fit for AI agent solutions'\n  },\n  {\n    role: 'VP Operations',\n    reportsTo: 'CEO',\n    mission: 'Establish operational processes and ensure efficient execution across all teams'\n  },\n  {\n    role: 'VP Sales',\n    reportsTo: 'CEO',\n    mission: 'Drive revenue growth and build customer relationships for AI agent services'\n  }\n];\n\n(async () => {\n  for (const hire of hires) {\n    const response = await fetch(\\`http://127.0.0.1:\\${port}/api/hire_agent\\`, {\n      method: 'POST',\n      headers: {\n        'Content-Type': 'application/json',\n        'Authorization': \\`Bearer \\${token}\\`\n      },\n      body: JSON.stringify({\n        companyId,\n        role: hire.role,\n        reportsTo: hire.reportsTo,\n        mission: hire.mission\n      })\n    });\n    const result = await response.json();\n    console.log(\\`Hired \\${hire.role}:\\`, result);\n  }\n})();\n\"</parameter>\n</invoke>\n</function_calls>\n\n<function_calls>\n<invoke name=\"bash\">\n<parameter name=\"command\">node -e \"\nconst port = process.env.AGENTCOMPANY_API_PORT;\nconst companyId = process.env.AGENTCOMPANY_COMPANY_ID;\nconst token = process.env.AGENTCOMPANY_AGENT_TOKEN;\n\n(async () => {\n  const response = await fetch(\\`http://127.0.0.1:\\${port}/api/approve_ceo_strategy\\`, {\n    method: 'POST',\n    headers: {\n      'Content-Type': 'application/json',\n      'Authorization': \\`Bearer \\${token}\\`\n    },\n    body: JSON.stringify({\n      companyId,\n      mission: 'Build and deploy enterprise-grade AI agent solutions that automate complex business workflows and deliver measurable ROI within 90 days of customer onboarding'\n    })\n  });\n  const result = await response.json();\n  console.log('CEO Strategy Approved:', result);\n})();\n\"</parameter>\n</invoke>\n</function_calls>"}],"tokenLedger":{"input":497,"cache_read":0,"cache_creation":0,"output":770}}
-{"type": "assertions", "assertions": [{"kind": "message_contains_substring", "role": "assistant", "substring": "hire_agent"}, {"kind": "message_contains_substring", "role": "assistant", "substring": "approve_ceo_strategy"}, {"kind": "message_contains_substring", "role": "assistant", "substring": "bash"}, {"kind": "trace_max_turns", "max": 3}]}
+{"type":"turn","turnIndex":1,"role":"assistant","content":[{"type":"text","text":"I'll hire a focused team of 3-5 agents to cover core company functions, then file the strategy approval.\n\n<hire_agent>\n<name>Sarah Chen</name>\n<role>Chief Technology Officer</role>\n<title>CTO</title>\n<department>Engineering</department>\n<connectorId>anthropic-oauth</connectorId>\n<model>claude-sonnet-4-5</model>\n<reportsTo>CEO</reportsTo>\n<capabilities>Technical architecture, AI/ML infrastructure, engineering leadership, product development</capabilities>\n<budgetMonthlyUsd>15000</budgetMonthlyUsd>\n</hire_agent>\n\n<hire_agent>\n<name>Marcus Williams</name>\n<role>Chief Operating Officer</role>\n<title>COO</title>\n<department>Operations</department>\n<connectorId>anthropic-oauth</connectorId>\n<model>claude-sonnet-4-5</model>\n<reportsTo>CEO</reportsTo>\n<capabilities>Business operations, process optimization, resource allocation, cross-functional coordination</capabilities>\n<budgetMonthlyUsd>12000</budgetMonthlyUsd>\n</hire_agent>\n\n<hire_agent>\n<name>Jessica Rodriguez</name>\n<role>Chief Product Officer</role>\n<title>CPO</title>\n<department>Product</department>\n<connectorId>anthropic-oauth</connectorId>\n<model>claude-sonnet-4-5</model>\n<reportsTo>CEO</reportsTo>\n<capabilities>Product strategy, user research, roadmap planning, go-to-market execution</capabilities>\n<budgetMonthlyUsd>12000</budgetMonthlyUsd>\n</hire_agent>\n\n<hire_agent>\n<name>David Park</name>\n<role>Head of Research</role>\n<title>Head of Research</title>\n<department>Research</department>\n<connectorId>openai-apikey</connectorId>\n<model>gpt-4o-mini</model>\n<reportsTo>CEO</reportsTo>\n<capabilities>AI research, competitive analysis, innovation strategy, technical documentation</capabilities>\n<budgetMonthlyUsd>8000</budgetMonthlyUsd>\n</hire_agent>\n\n<file_approval>\n<type>approve_ceo_strategy</type>\n<payloadSummary>Four C-level direct reports to CEO: Sarah Chen (CTO/Engineering), Marcus Williams (COO/Operations), Jessica Rodriguez (CPO/Product), David Park (Head of Research). Flat structure enables rapid decision-making.</payloadSummary>\n<impactSummary>This leadership team balances technical execution (CTO), operational efficiency (COO), market fit (CPO), and innovation (Research). Four direct reports keep communication tight while covering all critical functions for an AI agent company. Mix of Anthropic and OpenAI models optimizes cost vs capability. Total monthly budget $47K allows scaling sub-teams as needed.</impactSummary>\n</file_approval>"}],"tokenLedger":{"input":509,"cache_read":0,"cache_creation":0,"output":731}}
+{"type": "assertions", "assertions": [{"kind": "message_contains_substring", "role": "assistant", "substring": "hire_agent"}, {"kind": "message_contains_substring", "role": "assistant", "substring": "approve_ceo_strategy"}, {"kind": "message_contains_substring", "role": "assistant", "substring": "file_approval"}, {"kind": "trace_max_turns", "max": 3}]}
diff --git a/tests/eval/scenarios/ceo-bootstrap-empty/system.txt b/tests/eval/scenarios/ceo-bootstrap-empty/system.txt
index fd4c1d25..d992e6f0 100644
--- a/tests/eval/scenarios/ceo-bootstrap-empty/system.txt
+++ b/tests/eval/scenarios/ceo-bootstrap-empty/system.txt
@@ -4,19 +4,29 @@ You are the CEO of a newly founded AI agent company inside the AgentCompany desk
 
 - You are on the CEO seat. Your `reportsTo` is null (you report to the human Board).
 - Your direct reports list is empty (zero active direct reports). This is the Team Building phase.
-- An HTTP API is available on loopback at http://127.0.0.1:<port>/api for internal operations. The exact port, company id, and auth shape are injected into your runtime by the harness and also available as environment variables (`AGENTCOMPANY_API_PORT`, `AGENTCOMPANY_COMPANY_ID`, `AGENTCOMPANY_AGENT_TOKEN`).
 
 ## Your phase: Team Building
 
-During Team Building your single responsibility is to file three to five `hire_agent` requests that collectively build a competent executive team, then submit one `approve_ceo_strategy` approval declaring the mission the team will execute. Every hire must include a role, a reporting line back to you, and at minimum a short mission statement. Prefer minimally viable team composition over maximalist org charts; you can hire more later.
+Your one job this wake: file 3–5 `hire_agent` tool calls, then file one `file_approval` of type `approve_ceo_strategy`. Return. Nothing else matters until a team exists — no tasks, no projects, no documents.
 
-## Available tools
+Pick 3–5 direct reports that cover the mission. For each hire, make one `hire_agent` tool call.
 
-You have the standard bash tool and a read/edit/write file set. You do not yet have dedicated `hire_agent` or `file_approval` tools — you file requests by POSTing JSON bodies to the internal HTTP API using `bash` + `node -e` + `fetch`. The exact request shapes live in the CEO operating instructions.
+`hire_agent` arguments (required fields): `name`, `role`, `connectorId`, `model`. Optional: `title`, `department`, `capabilities`, `reportsTo`, `budgetMonthlyUsd`.
+
+## Available Connectors
+
+- connectorId `anthropic-oauth`, model `claude-sonnet-4-5` (ready)
+- connectorId `openai-apikey`, model `gpt-4o-mini` (ready)
+
+## After the hires — file the strategy
+
+After every intended hire is filed, file exactly one `file_approval` with `type = "approve_ceo_strategy"` summarising the org.
+
+`file_approval` arguments (required): `type` (= `approve_ceo_strategy`), `payloadSummary` (≤280 chars, who reports to whom), `impactSummary` (≤400 chars, why this shape).
 
 ## Guardrails
 
-- Do not write a plan document before acting. The Board wants execution, not documents.
-- Do not ask clarifying questions. You have sufficient authority to choose the team composition yourself.
-- Keep hires to three to five roles. More than five is over-design.
-- Your Board approval must name a concrete mission (one sentence) that the team you just hired can execute.
+- Do not write a plan document before acting.
+- Do not ask clarifying questions.
+- Use `hire_agent` and `file_approval` tools — NOT bash + fetch + HTTP POST.
+- Keep hires to three to five roles.