“Fully autonomous”
Humans still review, test, and carry the pager. Say “agent-assisted.”
Humans still review, test, and carry th…Evidence
Governance
Responsible claims
Keep outbound language tied to observable product behavior: routing tables, budget stops, diff sidebars, security gates, design audits, reviewer models. Anchor marketing, sales, and support claims so nobody promises magic off-script.
- Velocity: Say pilots “often shorten the loop between prompt and reviewed PR when routing + review defaults are set.” Avoid invented percentages.
- Quality: Say Review mode “surfaces structured feedback beside proposed changes before merge.” Quality still depends on tests and human judgment.
- Cost: Say budgets and routing “make spend legible and interruptible.” Savings require enforcement, not hope.
responsible-claims-overview.md - operating view
“FullyVelocity
“ZeroQuality
“ReplacesCost
“AlwaysCompliance
Governance
Claims we stand behind
Headline: “Your repo stays on your machine.” Precision: you work in a local workspace; inference providers read only the context you attach to prompts and tool actions - there is no architecture that uploads the entire disk as one blob.
- Velocity: Say pilots “often shorten the loop between prompt and reviewed PR when routing + review defaults are set.” Avoid invented percentages.
- Quality: Say Review mode “surfaces structured feedback beside proposed changes before merge.” Quality still depends on tests and human judgment.
- Cost: Say budgets and routing “make spend legible and interruptible.” Savings require enforcement, not hope.
- Compliance: Say local inference + audit trails “fit programs that separate data tiers.” Legal still signs off.
- “Fully autonomous”: Humans still review, test, and carry the pager. Say “agent-assisted.”
Active focus:
Governance
Scope
Risk
Output
responsible-claims-overview.md
Capturing...
// Focus:
Claims we stand behind
1) Pair every superlative with a UI surface: If you cannot screenshot it, downgrade the adjective. 2) Name the audience + environment: Regulated orgs, agencies, and hobbyists hear different promises. 3) Link to limits: Responsible claims plus legal docs beat a footnote wedged under a signup button. 4) Revisit quarterly: Model vendors change pricing and policies; refresh copy when they do.
1“Fully
2“Zero
3“Replaces
4“Always
5Review
What Governance stakeholders get operationally
“Zero risk / guaranteed safe”
Models hallucinate. Our gates reduce whole classes of bugs; they do not prove security.
Models hallucinate. Our gates reduce wh…Evidence
“Replaces AppSec / QA”
Kodus supports those teams; it is not a substitute for policy and tests.
Kodus supports those teams; it is not a…Evidence
High-signal placements
Governance rollout focus
Headline: “Your repo stays on your machine.” Precision: you work in a local workspace; inference providers read only the context you attach to prompts and tool actions - there is no architecture that uploads the entire disk as one blob.
“Fully autonomous”
Humans still review, test, and carry the…“Zero risk / guaranteed saf…
Models hallucinate. Our gates reduce whol…“Replaces AppSec / QA”
Kodus supports those teams; it is not a s…“Always offline”
Only true when every model endpoint is lo…Velocity
Buyer-ready evidence
Pilot
Review
Evidence
Scale
How it works
Headline: “Your repo stays on your machine
Headline: “Your repo stays on your machine.” Precision: you work in a local workspace; inference providers read only the context you attach to prompts and tool actions - there is no architecture that uploads the entire disk as one blob.
1) Pair every superlative with a UI surface
If you cannot screenshot it, downgrade the adjective.
2) Name the audience + environment
Regulated orgs, agencies, and hobbyists hear different promises.
3) Link to limits
Responsible claims plus legal docs beat a footnote wedged under a signup button.
FAQ
FAQ
Can we quote customer logos with hard ROI?
Only with written approval and attributable metrics. Anything else violates this framework.
Are competitive comparisons fair game?
Stick to observable behaviors - “Kodus exposes diffs inline” vs naming a rival’s weakness you cannot verify.
Who owns updates to this page?
Product marketing maintains copy; legal and security review changes before major launches.
What do we say when something is on the roadmap?
Say “on the roadmap,” not “shipping next week.”
How should we pilot?
Pick one bottlenecked workflow with named reviewers, run two cadence loops, revisit metrics.
Does tooling replace approvals?
No - Kodus complements review, scanners, budgets, and your escalation paths.
Pricing
Pricing
Use the same Kodus plans, tokens, and routing controls across workflows and posture.
Best to Start
Starter
For individual usage.
$20/mo
- 10M tokens / month
- 300 iterations / month
- Standard model routing
- Chat history + projects
- Community support
Team
For small teams.
$100/mo
- 70M tokens / month
- 2,500 iterations / month
- Full routing + Review + Strategy
- Bring your own local model
- Teams (up to 2 members)
- Priority support
- Audit log access
Scale
For larger organizations.
$200/mo
- 300M tokens / month
- 7,500 iterations / month
- Unlimited team members
- All models + custom routing
- Dedicated support channel
- Early access to beta features
- No annual contract
- Tokens reset monthly
- Switch plans anytime
Have invite code? Get Access Now