survol

← All articles · Agentic development

Agentic development

The approved spec IS the prompt: why we never type into a coding agent any more

Agentic development makes you lose the mental map of your product. Here is the conviction that gave birth to Survol: describing a feature once, properly, beats ten throwaway prompts.

A
Adrien Torris 14 June 20268 min read
The approved spec IS the prompt with Survol.ai

A year ago I was steering all my projects with prompts in a terminal. A feature was born in one message, fixed in a second, drifted in a third. Six weeks later, three perfectly simple questions had become unanswerable: what is actually done? in which version? on which branch?

This is not a problem with the coding agent - it does its job remarkably well. It is a problem with the tooling around the agent. When you delegate the code, you need, more than ever, to keep the product view. And the throwaway prompt is the exact opposite of a product view: ephemeral, unversioned, unreadable three days later.

You cannot steer a product with a terminal history.

The throwaway prompt, that false friend

The direct prompt is seductive because it is immediate. But it has three fatal flaws as soon as a team - or simply next month's version of you - has to pick up the thread:

The inversion: the spec first

Survol's proposal fits in one sentence: you describe a feature the way you would to a colleague, you approve it as a team, and that approved spec becomes the instruction sent to the agent. You never type the prompt - it is generated, refined and traced from what you have already written and decided.

Concretely: every feature has a version history (v1.0, v1.1, v2.0…) with the changes requested in between. The version is the unit of truth - not the author, not the prompt.

That shift has an unexpected but decisive consequence on costs. When the spec is the object of work, you can calibrate context down to what is strictly needed: the spec, the settled decisions, the files actually concerned. Nothing more.

# What Survol sends to the agent, generated from the approved spec:
context:
  feature: "Promo codes & gift cards"
  version: "v2.0"
  decisions: ["cannot be combined with sale prices"]
  files: ["src/Pricing/Promo.cs", "src/Checkout/Cart.cs"]
model: "selected automatically for the task"
The prompt is no longer written by hand: it is derived from the spec.

Where do humans fit in?

Inverting the flow does not mean taking control away from teams - quite the opposite. Product decisions are discussed before a session is launched. Your developers can still write code directly: manual branches, commits and merge requests are detected and attached to the right feature, with no informer's tone. And at any moment, a human expert review can turn its findings into tasks for the agent.

The approved spec IS the prompt with Survol.ai

What changes day to day

  1. You write the feature once, properly.
  2. The team settles the open decisions.
  3. The agent builds it on its branch, and you follow live.
  4. You approve the preview - or your feedback becomes the next version.

After a few weeks, the question "what is actually done?" has an answer, permanently. That is all we were asking for in the first place - and it is precisely what the throwaway prompt will never give you.

#agentic-development #product #specs
A

Adrien Torris

Founder of Survol

A developer turned agent orchestrator. I write about steering products in the age of agentic development, and about the making of Survol.

Don't miss the next article

One email a month, our best field notes on agentic development and what's new in Survol.