Model routing for AI agents: stop overspending on simple tasks

from prysm import Prysm

client = Prysm()

def agent_step(step_type: str, context: str) -> str:
    """Route each agent step to the right model."""

    # Classify which step type we're in
    routing_mode = {
        "plan":        "quality",    # Use the best model for planning
        "reason":      "quality",    # Use the best model for reasoning
        "summarize":   "agility",    # Budget model for summarization
        "classify":    "agility",    # Budget model for classification
        "synthesize":  "balanced",   # Mid-tier for final synthesis
    }.get(step_type, "balanced")

    resp = client.chat.completions.create(
        model="auto",
        messages=[{"role": "user", "content": context}],
        extra_body={"routing_mode": routing_mode},
    )
    return resp.choices[0].message.content

result = client.agents.run(
    goal="Research and summarize the top 5 papers on retrieval-augmented generation",
    max_cost_usd=0.25,     # Hard stop at $0.25 — never exceeded
    max_steps=15,
)

print(result["output"])
print(f"Steps: {result['steps_taken']}  Cost: ${result['cost_usd']:.4f}")
print(f"PrysmProof: {result['proof']['proof_hash']}")
# Steps: 8  Cost: $0.0847
# PrysmProof: sha256:a1b2c3d4e5f67890

# BRAIN.md
max_cost_per_request: 0.10      # Never spend more than $0.10 on a single call

rules:
  - when: "code"
    model: "claude-sonnet-4.5"  # Code-specialized for coding tasks
  - when: "reasoning"
    model: "deepseek-r1"        # Strongest reasoning model for math/logic
  - when: "summarize"
    routing_mode: agility       # Budget model for summarization

blocked:
  - gpt-5.2-pro               # Too expensive for most tasks

# BRAIN.md is auto-discovered from the repo root
client = Prysm()  # automatically reads ./BRAIN.md

# All calls now respect the rules above
resp = client.complete("Prove that sqrt(2) is irrational")
# Routed to deepseek-r1 (reasoning rule matched)

preview = client.route(
    "Summarize this 2000-word article",
    brain={"max_cost_per_request": 0.10, "rules": [{"when": "summarize", "routing_mode": "agility"}]},
)
print(preview["routing"]["model"])    # mistral-nemo
print(preview["routing"]["why"])      # "summarize rule + agility mode"
print(preview["estimated_cost"]["est_1k_tokens"])  # 0.00002 USD

savings = client.savings(baseline="gpt-5.2-pro")
print(f"Agent spent ${savings['actual_usd']:.4f} vs. ${savings['baseline_usd']:.4f} baseline")
print(f"Saved {savings['saved_pct']}% by routing")