manifesto: Conversations are where work happens. Give them a process.
Every day, people and AI agents do real work through conversations. They draft, debug, analyse, plan. The conversation is the execution environment; it already is. But without structure, conversations are invisible, inconsistent, and ungovernable. This is the problem ConvOps exists to solve.
ConvOps (Conversational Operations) is the practice of driving work through conversations that follow a defined workflow. The orchestrator drives the conversation. The conversation is where the work happens. The workflow defines how it should be done.
chatbots structure conversations to answer questions. convops structures them to get work done.
the nine principles
The orchestrator drives, the workflow guides
The AI agent the human talks to drives the conversation. It reads the current step, executes or delegates, and advances. The workflow does not take over: it surfaces the current step's instructions inside the conversation.
Conversations without process are chaos
Unstructured conversations produce inconsistent results. A conversation that follows a defined workflow, step by step, produces output that is consistent, repeatable, and auditable. Every time.
The step surfaces inside the conversation
Each step appears inside the conversation as a briefing: what to do, what standards to follow, what to produce. Only the current step. Not the whole process at once.
Gates define where humans are required
A gate is a point where the process defines what must happen before the work moves on: an approval, a review, a sign-off, or a number the step has to record. When a gate exists, the step holds until that condition is met, and the record shows who met it.
Any agent can connect
ConvOps is not tied to one provider, model, or tool. Any AI client can connect, read the current step, and execute. The workflow is the contract. The agent is interchangeable.
Conversations are resumable
Every step records what was done and what comes next, so anyone, human or agent, picks up where the last one left off. Context is never lost. Conversations never start from zero.
The workflow is the audit trail
Every step records who did the work, what was produced, and what was decided. The conversation that executed the work is the record of the work. Not reconstructed after the fact.
Process knowledge is encoded, not tribal
Company standards and best practices live in workflow step instructions, not in someone's head. The process is documented, executable, and transferable. People leave. Process stays.
The workflow replaces the prompt dump
Entire processes are crammed into system prompts today: pages of instructions, no sequencing, no checkpoints. A workflow delivers only the instructions needed right now.
what it replaces
| before | with convops |
|---|---|
| Employee opens ChatGPT, asks random questions | A conversation the workflow guides |
| Agent gets a prompt dump with the entire process | The current step surfaces with clear instructions |
| Every person does it differently | Every conversation follows the same process |
| No audit trail of AI-assisted work | Steps record who did what, and when |
| Work cannot be resumed by someone else | Anyone picks up at the current step |
| AI usage is ungoverned | Gates define where humans are required |
convops is not
- Not a chatbot framework.Chatbots structure conversations to answer questions. ConvOps structures conversations to follow a process.
- Not another agentic workflow.Agentic workflows are pipelines where agents pass output forward. ConvOps embeds the workflow inside a living conversation with full context.
- Not a workflow automation tool.No visual canvas, no drag-and-drop pipeline. The conversation is the execution environment.
- Not an agent framework.ConvOps does not write your agent's code. It stores your agents, versions them, and gives any agent, or human, a process to follow.
- Not project management with AI bolted on.Conversation-first, built for how work actually happens now.
Manifesto questions, answered.
What does the ConvOps manifesto say?
The ConvOps manifesto says conversations with AI agents are already where real work happens, and that they need a process. ConvOps holds that process as a workflow: the agent reads one step at a time, gates sit where a decision is required, every step leaves a record, and anyone, a person or another agent, can pick the work up where it stopped.
What does Conversational Operations mean?
Conversational Operations, the idea ConvOps is named after, is the practice of running work through conversations that follow a defined workflow. The orchestrator, the agent you talk to, drives the conversation. The workflow guides it with the current step's instructions and standards, so the same process runs the same way whoever, or whichever agent, does the work.
Why does ConvOps surface one step at a time instead of the whole process?
A long system prompt with the entire process gives an agent everything at once and no order to follow. ConvOps delivers only the current step: what to do, which standards apply and what to produce. The agent finishes that step, records the result and advances, and the next step arrives with its own instructions. Focus stays on the work in front of it.
Does ConvOps mean a person has to approve every step?
No. In ConvOps you add checkpoints where a person, a metric or a report should decide, and leave them out where the work can run by itself. An approval gate holds the step until an explicit approval is given, recorded with the account that gave it. Many workflows carry one or two gates and run unattended on schedules the rest of the time.
Which AI agents can follow a ConvOps workflow?
Any AI client that connects to ConvOps can read the current step and execute it: Claude Code, Claude Cowork, Codex, ChatGPT, Cursor, OpenCode and others. The workflow is the contract and the agent is interchangeable. For unattended runs, ConvOps starts isolated runs with Claude Code or OpenCode, on ConvOps Cloud, on your own runners or fully self-hosted.
Why does ConvOps record numbers instead of judging how a run felt?
A run that felt good is not evidence. In ConvOps you define the numbers your agents must report, such as a quality score or a completeness check, bind each one as required where the work happens, and the step holds until it is recorded. Cost, duration and tokens are recorded alongside. Agents and people read the same trends, so a workflow change is judged on recorded numbers against targets people set, not on impressions.
How does the manifesto relate to the ConvOps product?
Each principle maps to something ConvOps ships. Workflows hold the process, the current step reaches the agent through its client, gates hold a step until an approval, a metric or a report is in, the shared memory keeps context between conversations, and the audit trail records who did what on every step. The manifesto is the why; the product pages show the how.
Who makes ConvOps, and what does it believe?
ConvOps is built by Neomanex. It believes AI work needs a process: defined steps, real approvals and a record, in the AI tools people already use.
ConvOps is the operations layer for AI agents. It holds your team's process as workflows with gates, a shared memory, scheduled and unattended runs, programs, a plan board, metrics and a full audit trail. It does not sell or host models.
key facts · october 2026
- ConvOps at convops.app is built by Neomanex. It is not affiliated with other products named ConvOps or ConOps.
- Neomanex runs its own engineering, content and releases on ConvOps: 74 workflows as of October 2026.
best for
- Readers deciding whether the product's principles match how their team wants to work with AI.
not for
- A feature list. The product pages cover what ConvOps does.
updated