Design partners
Join the design-partner program.
We’re looking for a few engineering teams to test whether deciding first and delegating the running of agents saves real effort on real changes, measured honestly against your best current setup.
What this shows
- Open question · for both owners: Should Checkout receive a duration or an absolute timestamp?
- Absolute timestamp, UTC: Unambiguous across retries; Checkout computes the time remaining.; Duration in seconds: Simple to display; drifts with network latency and retried requests.
- Unknown: Clock behavior on restart: candidate for an isolated exploration
Who fits
B2B SaaS engineering organizations of roughly 50 to 200 engineers.
- Coding agents in active use, with real time spent operating them.
- Recurring decisions that cross team boundaries, such as an API between a provider and a consumer team.
- A versioned OpenAPI definition and a runnable contract or integration test.
- Decision owners who can be reached, and a budget holder open to discussing continuation.
What you get
- A measured picture of where effort goes on your changes, including agent operation.
- The results reviewed with your team and your budget owner, not just reported.
- Comparisons against your best current setup, never a weakened baseline.
- A dated decision at the end, to continue, revise or stop, with the reasoning.
What we ask
- A champion’s time, capped and accounted for.
- Recent change artifacts and reviewers for measurement, under a written agreement.
- An honest baseline: your normal workflow and your best improved one.
- Candid feedback, including the reasons to stop.
Four stages, each earned by the one before.
Nothing advances on enthusiasm. Each stage continues only on evidence, and any of them can end with a clear stop decision.
Conversation
We reconstruct a recent change with you before showing anything: how decisions were found, who owned them, and how much time went to operating agents.
Assisted comparison
Historical or sandboxed changes, compared three ways: your current workflow, your best improved setup, and the Assent loop run partly by hand. Every analyst minute is recorded.
Shadow analysis
The prototype would analyze live changes without blocking them, and its calls would be compared with your reviewers’. Merges stay human.
Bounded evaluation
Four to six weeks on one nominated relationship. Assent would run the implementation; people approve decisions and merge. No production execution or automatic merge.
The evaluation stage is planned as a paid, bounded engagement, and every offer states who pays for agent compute. Compare the programs
Data and exit
Your code, your terms, a clean exit.
- No access to code without a written agreement on scope, storage, providers, region and retention.
- Read-only access to the repositories you select, first.
- Access and grants would be revoked when the engagement ends, and data deleted on the agreed schedule, including logs and backups.
- Your name, quotes or results are never published without separate permission.
Can we use Assent today?
Not yet. Assent is pre-launch: a local prototype, not yet run live. We’re forming a small design-partner cohort to test the first workflow. It starts with conversations about recent changes. Then we reconstruct historical or sandboxed changes with you, partly by hand and under agreed data terms, and compare them with your current workflow and your best improved one.
What would a first evaluation involve?
One nominated cross-team API relationship in one GitHub repository, with a versioned OpenAPI definition, identified provider and consumer owners, and a runnable contract or integration test.
Over four to six weeks we’d aim for five to ten eligible real changes, compared with your normal workflow and your best improved one, including your agent vendor’s own orchestration where you have it. People approve decisions and merge throughout.
Which coding agents does Assent run?
The first managed adapter is planned to be Claude Code, running in an isolated runner that Assent would operate. A second adapter would follow only after it passes control-equivalence tests.
Agents you run yourself, outside Assent, could receive an advisory export. We make no claim of mediated actions, reliable pause or complete audit for those runs.
Will it merge or deploy on its own?
Not in the first evaluation: people approve decisions and merge. Policy-gated merge and release promotion are later steps, enabled per change class only with evidence, explicit customer policy and an authorized policy owner’s adoption. A critical incident would step a class back immediately.
Where does our code go?
We would read only the repositories and paths you select. Selected snippets and contracts would go to agreed snapshot storage and an approved analysis provider. During a run, the code an agent reads would go to its model provider, under the account the execution model names; with your own accounts, your provider’s terms apply.
The provider, region and retention of each would be disclosed. Filtering secrets reduces what reaches a model but can’t guarantee none does, so we would keep the scope small rather than rely on scanning.
What has to be agreed before you read our code?
In writing: the repositories and paths, storage location, retention and deletion, the model and agent providers and their data terms, the execution model, who can revoke access, and incident contacts. If those aren’t agreed, nothing is read.
Access would start read-only, for discovery and shadow analysis. More permissions would come only with a capability that needs them, such as opening pull requests once managed implementation begins. Synthetic demonstrations need none of it.
How is this different from our agent vendor’s planning or orchestration?
There’s real overlap, and we won’t pretend otherwise. Our hypothesis is that one continuing chain (the decision, its owner, a scoped grant, the agent work run under it, and the evidence it produced) saves more total effort than orchestration or decision records alone.
The evaluation would compare against your best configured setup. If that does as well, the result should say so.
Who pays for agent compute?
Every offer states it up front: either your organization’s own provider accounts, or usage managed by Assent with a visible meter and caps. Personal subscriptions would never be pooled.
Does Assent measure individual developers?
Not individually. An evaluation would record time by person or role so that effort can be counted, but would report it only at team level, and nobody would be ranked.
What would make you stop?
If teams can’t produce recurring examples; if improved existing tools, including vendor-native orchestration, perform as well; if buyers would rather govern their own agents than have them operated; if execution cost per delivered change can’t be priced sustainably; if authority setup needs continuing expert consulting; or if useful trials don’t lead to paid continuation.
Tell us about your team.
What happens next
- We reply by email.
- A first conversation about one recent change. No demo first.
- If there’s a fit, scope and data handling are agreed in writing before anything else.