Ho smesso di usare Opus per tutto. Uso ancora Claude, Kimi e GPT. I costi dell'IA sono scesi del 43% da un giorno all'altro

1Look at your last 30 Droid tasks. Sort them into two groups:
2
3Frontier-worthy: tasks involving system architecture, auth, payments, security,
4cross-service dependencies, anything where being wrong costs time to debug or
5reverts. Complex refactors over 100 lines of business logic.
6
7Routine: doc updates, config changes, adding tests to existing functions,
8small bug fixes with clear specs, copyright headers, README edits,
9boilerplate generation, simple migrations.
10
11Count each group.
12
13Based on Factory's session-level data:
14"reset my password" type tasks: Opus $0.84 vs routed $0.09. 89% cheaper.
15"add copyright header" type tasks: Opus $0.62 vs routed $0.12. 81% cheaper.
16
17Multiply your routine task count by that difference.
18That gap is your current model selection tax.

1Pull your last month of Droid session logs.
2
3For each session:
4- Task type (from Rule 1 classification)
5- Model used
6- Cost
7
8Calculate:
9- Total spend on routine tasks using frontier models
10- What those tasks would cost on efficient models (apply 80-90% reduction)
11- Monthly savings available from routing
12
13This is your baseline before enabling Factory Router.
14Most teams find 30-50% of sessions are routine work running on frontier models.

1The way you describe a task signals its complexity to any routing system.
2
3Low-complexity signals (routes to efficient models):
4- "Simple config update, no business logic: change timeout in config.yaml from 30 to 60"
5- "Add missing JSDoc comments to the utility functions in /helpers"
6- "Update the README to reflect the new deployment steps"
7
8High-complexity signals (routes to frontier):
9- "Refactor the auth middleware to support our new SSO integration across 3 services"
10- "Debug the race condition in the payment processor that only appears under concurrent load"
11- "Redesign the rate limiting system to handle per-tenant thresholds"
12
13Specific, context-rich task descriptions improve routing accuracy.
14Vague descriptions get routed conservatively to frontier models.

1Formula for estimating Factory Router savings:
2
3Monthly sessions: [N]
4Average cost per session without routing: [Opus baseline in $]
5Routine task percentage: [% from your Rule 1 audit]
6Routine cost reduction: 80-90%
7
8Monthly savings estimate:
9N × baseline × routine% × 0.85 = monthly dollars recovered
10
11Annual: multiply by 12.
12
13For a team running 5,000 sessions/month at $2.87 average with 40% routine work:
145,000 × $2.87 × 0.40 × 0.85 = $4,879/month = $58,548/year
15
16This is the minimum. Missions (long-running autonomous work) compound the savings further.

1Before enabling routing, define what must stay on frontier models for your codebase.
2
3Write this once. Paste it as your routing guidance baseline:
4
5"The following always require frontier models:
6- Any changes touching [auth/payments/security layer]
7- Cross-service refactors with more than [N] files
8- Changes to CI/CD pipeline configuration
9- Database schema migrations
10- Anything flagged as [P0/critical] in our issue tracker
11
12Everything else is eligible for routing to efficient models."
13
14This becomes your routing policy document.
15You update it as you learn what needs frontier treatment in your specific codebase.

1In Factory CLI or Desktop App:
2
31. Open the model picker
42. Select "Factory Router"
53. Done.
6
7No configuration required to start. Router uses default routing logic immediately.
8
9To verify it's active:
10Run a simple task ("update a comment in this file").
11Check the session log for model attribution.
12You should see an efficient model handling it, not Opus.
13
14If you see Opus on a simple task, verify Router is selected and not a specific model override.

1Routing guidance is advisory. It helps the Router make better decisions
2for your specific codebase. It does not force a model.
3
4Paste this as your routing guidance starting point and edit for your stack:
5
6"Auth, payments, and security changes: frontier models.
7Database migrations and schema changes: frontier models.
8API contract changes that affect external consumers: frontier models.
9
10Documentation updates: efficient models.
11Adding tests to existing functions: efficient models.
12Config and environment variable changes: efficient models.
13Boilerplate generation and scaffolding: efficient models.
14Code comments and JSDoc: efficient models.
15README and changelog updates: efficient models.
16
17Everything else: Router decides based on task context."

1For teams running agents at scale, routing guidance becomes a governance document.
2
3Standard template for regulated industries (banking, healthcare, enterprise SaaS):
4
5"High-sensitivity routing rules:
6- Anything touching [PII / financial data / auth] = frontier only
7- Any external API changes = frontier only
8- Production deployment scripts = frontier only
9- Incident response tasks = frontier only
10
11Standard routing:
12- Development, staging, and test environments = Router decides
13- Internal tooling and automation = efficient models preferred
14- Documentation, reporting, and communication = efficient models
15
16Override policy:
17Any developer can request frontier on a task.
18Router treats this as a hard override, not advisory.
19Log all frontier overrides for monthly review."
20
21Save this as ROUTING_POLICY.md in your project root.
22Reference it in your CLAUDE.md or equivalent context file.

1Missions are Factory's long-running autonomous tasks.
2Hours or days of work. No supervision required.
3
4With Factory Router enabled, Missions benefit from the same routing logic.
5Each step in a Mission gets routed appropriately.
6Simple steps in a complex Mission run on efficient models.
7The Mission pays frontier rates only when frontier reasoning is actually needed.
8
9To configure:
10Enable Factory Router before starting any Mission.
11Add routing guidance that reflects the Mission's complexity profile:
12
13"This Mission involves [high-complexity core work] and [routine supporting tasks].
14Core work (architectural decisions, security analysis): frontier.
15Supporting work (documentation, config, boilerplate): efficient models.
16Use the most efficient model available for any step
17that doesn't require the reasoning specified above."
18
19Long Missions see proportionally larger savings because they accumulate more routine steps.

1Factory Router routes across providers for reliability.
2If one provider path degrades, sessions continue through a healthy provider.
3
4For enterprise teams with uptime requirements:
5
6"Reliability routing policy:
7- Primary provider per model: [list your preferred providers]
8- Failover trigger: any request failing or exceeding [N] second latency
9- Failover behavior: same model, different provider if available.
10  If same model unavailable, escalate to next frontier model.
11- Dedicated TPM: confirm with Factory account team for your tier.
12- Target: 99.9%+ request reliability.
13
14Log all failover events. Review weekly for provider health patterns."

1Set a weekly routine to track Router performance.
2
3Check in Factory session logs:
41. Total sessions this week
52. Model distribution (what % went to each model)
63. Cost with routing vs baseline (Opus on everything)
74. Any sessions where Router escalated to frontier (quality signal)
8
9Report format:
10> sessions: [N]
11> efficient model usage: [%]
12> frontier model usage: [%]
13> actual spend: $[amount]
14> baseline (all Opus) would have been: $[calculated]
15> weekly saving: $[amount]
16> escalations to frontier: [N] (review for routing guidance improvements)
17
18If escalation rate is above 10%, review your routing guidance.
19Too many escalations means routine tasks are being described as complex.

1Before deploying Factory Router for your full team, run Factory's Agent Readiness assessment.
2
3It evaluates 100+ signals across:
4- Codebase health (test coverage, CI reliability, documentation)
5- Workflow maturity (PR process, code review standards, deployment pipeline)
6- Team readiness (familiarity with agentic tools, existing automation)
7
8Use the output to prioritize which workflows to route first.
9
10High-readiness workflows: deploy Router immediately, full routing enabled.
11Medium-readiness workflows: deploy Router with conservative guidance, more frontier tasks.
12Low-readiness workflows: build readiness before routing.
13Agentic tools on unprepared codebases spend more time on frontier models correcting errors.
14
15Router savings are highest in high-readiness environments.

1Factory Router draws from a pool of frontier and efficient models.
2The pool you configure affects the routing options available.
3
4Recommended starting pool:
5
6Frontier tier (complex work):
7- Claude Opus (latest version)
8- GPT-5.2 (if in your approved vendor list)
9
10Efficient tier (routine work):
11- Kimi K2.6 (best value per F1 point for code tasks)
12- MiniMax M2.7 (lowest cost for simple tasks)
13
14Add models as you validate performance on your codebase.
15Start with the two-tier structure.
16Expand to three tiers (frontier / mid / efficient) once you have routing data.
17
18Document which models are approved for which compliance requirements.
19If your enterprise restricts certain model providers, configure the pool accordingly.
20US-hosted open-source models are available through Factory for environments requiring data residency.

1Factory works in CI pipelines. Routing applies there too.
2
3Add Factory Router to your GitHub Actions workflow:
4
5For pull request reviews:
6"Route PR review tasks by file change scope.
7- Security and auth file changes: frontier models
8- Test files: efficient models
9- Documentation changes: efficient models
10- Mixed PRs: route section by section if possible, otherwise frontier for the full review"
11
12For automated QA:
13"Route QA tasks by test complexity.
14- Critical path end-to-end tests: frontier models
15- Unit test generation: efficient models
16- Regression test suites: efficient models"
17
18CI routing compounds savings because it runs on every commit.
19The cost difference between Opus and Kimi K2.6 on test generation across 100 daily commits is material.

1Routing guidance should evolve as your codebase and team grow.
2
3Monthly review agenda (30 minutes):
4
51. Cost report: actual vs baseline, savings trend
62. Escalation analysis: which tasks escalated and why
73. Routing guidance update: does current guidance still reflect codebase complexity?
84. New model evaluation: any new models in the pool worth adding?
95. Team feedback: are developers overriding Router frequently? Why?
10
11Questions that signal your routing guidance needs updating:
12- Escalation rate above 15%: guidance is too aggressive toward efficient models
13- Escalation rate below 2%: guidance may be too conservative, leaving savings on the table
14- Developer override rate above 20%: Router is not matching developer expectations
15
16Update ROUTING_POLICY.md after every review.