Agent instructions

The agent_instructions field on POST /v1/run is a natural-language directive that gets incorporated into system prompts at every agent layer — orchestrator, strategist, persona agents, and block operators. Use it to shape tone, depth, scope, and citation requirements without having to pre-configure block types.

Examples

Instruction	Effect
`"Be thorough, verify all claims with 2+ sources"`	More personas spun up, verification steps inserted
`"Prioritize speed, minimal verification"`	Single persona, cross-checks skipped
`"Write for a C-suite executive audience"`	Executive tone across all outputs
`"Focus on European markets only"`	Research scoped geographically
`"Include source citations for every claim"`	Citation requirements injected into per-block prompts

Usage

curl -X POST https://api.getspine.ai/v1/run \
  -H "X-API-KEY: sk_spine_..." \
  -F "prompt=Analyze the competitive landscape for AI coding tools" \
  -F "template=deep_research" \
  -F "agent_instructions=Be thorough, verify all claims with 2+ sources. Write for a technical audience."

Agent instructions are additive to templates and custom blocks — you can combine all three in a single request.

Block types File uploads

Get Started

Concepts

Use with agents

Endpoints

Resources

Python SDK

TypeScript SDK

Runs

Canvas

Examples

Usage

​Examples

​Usage

Examples

Usage