Build an Agent Workflow: Research, Brief, Draft, Approve
Four Stages, One Artifact Between Each, and a Human Decision Where It Counts
Short answer
An AI marketing agent workflow works best in four stages: research, brief, draft, approve. The agent does the collecting and first drafts, a person signs off the brief before drafting starts, and nothing ships without approval. Each stage hands over a written artifact, so errors are caught where they are cheap.
1. What does a four-stage agent workflow look like?
Research produces a dated evidence note, the brief turns it into one decision, drafting turns the brief into channel copy, and approval is a person checking the draft against the brief. Two human checkpoints: after the brief and before publishing.
| Stage | Input | Output artifact | Who decides |
|---|---|---|---|
| Research | A bounded question and named sources | Evidence note: findings with dates and links | Agent collects, person skims |
| Brief | The evidence note plus your playbook | One-page brief: goal, audience, message, proof, call to action | Person approves or edits |
| Draft | The approved brief plus brand voice rules | Channel drafts with the brief line each one serves | Agent drafts, person picks |
| Approve | Drafts plus the brief | Approved post, scheduled or published | Person, always |
The shape matters more than the tools. You can run this with a chat assistant and a shared folder, with an agent in a terminal, or inside a marketing platform. What makes it work is that no stage starts from a vague instruction, and no draft is written before a person has agreed on what it is for.
2. How should the research stage be scoped?
Give the agent a closed question, a named list of sources and a time window, and ask for findings with dates and links. Open questions like find everything about our market produce confident summaries of whatever was easiest to reach.
A good research request reads like this: what did Veltrix and Sondera publish about pricing between September 1 and September 28, from their websites, their LinkedIn company pages and their current Meta ads, with one line per finding and a link. It has names, sources and a window, so the agent can finish and you can check the work.
The failure mode is well documented: an agent cannot tell you what it did not find, so an open question returns a partial picture presented as a complete one. The guide on delegating research to agents covers where the line sits in more depth.
Ask the agent to structure the evidence note as:
- Finding, in one sentence.
- Source link and the date it was published or observed.
- Whether it is a direct quote, a number or the agent's interpretation.
- A short list of sources it tried and could not reach.
3. What goes into the brief, and why does a person approve it?
A goal, an audience, the one message pillar the content serves, the proof that supports it, and a call to action. A person approves it because the brief is where strategy gets decided, and deciding strategy is not the agent's job.
| Field | What to write | Example |
|---|---|---|
| Trigger | The finding from research that prompted this | Veltrix now leads its Meta ads with its entry plan cut from $39 to $33 a month |
| Goal | What the content should change, in one line | Keep switching intent from turning into price comparison |
| Audience | Which ICP, at which stage | Operations leads evaluating tools this quarter |
| Message pillar | One pillar from your message house, by name | Setup in a day, not a month |
| Proof | Evidence you are allowed to use, with its source | Median onboarding time from your own product data |
| Call to action | The single next step | Book a fifteen-minute setup walkthrough |
| Channels and count | Where and how many pieces | Two LinkedIn posts, one email, one ad variant |
| Not saying | Claims to avoid | No direct price comparison, no naming Veltrix |
The approval is quick, often two minutes, but it is the most valuable two minutes in the workflow. Approving a brief is cheap; discovering at the draft stage that the angle was wrong costs every draft. The Not saying row is where most brand and legal problems are prevented.
4. How do I keep drafts on brief?
Give the drafting step only the approved brief and your voice rules, ask for two or three variants per piece, and require each draft to name the brief line it serves. Drafts that cannot point to the brief are off brief.
Narrow input is the lever. A drafting step that sees the whole research note will drift toward whatever was most interesting in it. A drafting step that sees only the approved brief, the brand voice rules and your content policy lines will write to the pillar you chose.
Instructions that keep drafts honest:
- Write two or three variants per piece, each with a different hook, all serving the same pillar.
- Start each draft with the pillar and proof line it uses, so the reviewer can check it at a glance.
- Use only the proof listed in the brief. If a claim needs a number that is not there, write [NEEDS SOURCE].
- Respect the channel: length, format and any character limits for the platform.
5. What does the reviewer check before approving?
Five things: it serves the brief, every claim is backed by the listed proof, it sounds like you, it respects the Not saying row, and the link and timing are right. If any fails, send it back with the specific line.
- Check it against the brief. Read the pillar line at the top of the draft, then the draft. If the draft argues something else, reject it rather than editing it into shape.
- Check every claim. Each number, customer outcome or comparison should trace to the proof field. Anything that does not is removed, however good it sounds.
- Read it aloud for voice. Fluent is not the same as on-brand. Listen for phrases your team would never say, and for the generic openers AI drafts default to.
- Check the Not saying row. Competitor names, price comparisons and restricted claims are where approvals matter most. This is the step that protects the brand.
- Check link, tracking and timing. Confirm the destination, the UTM tags and the scheduled time, then approve. Publishing is the only step that cannot be undone.
6. Where do agent workflows usually break?
At the handoffs: research that answers a different question, briefs approved without reading, drafts that see too much context, and approvals that become rubber stamps. Each has a simple fix.
| Where | What goes wrong | Fix |
|---|---|---|
| Research | Answers an easier question than the one asked | Name sources and a window, ask for sources it could not reach |
| Research to brief | Interpretation presented as fact | Label each finding as quote, number or interpretation |
| Brief | Approved without reading | Keep it to one page and require an edit or an explicit yes |
| Draft | Drifts to the most interesting research detail | Feed only the approved brief and voice rules |
| Approve | Becomes a rubber stamp after a few good weeks | Keep the five checks, rotate the reviewer occasionally |
Oppira runs this loop inside one system: Intel supplies the dated research, the agent proposes playbook edits and content plans, Studio drafts in your brand voice to your message pillars, and nothing is published or changed without your approval. The stages are the same whichever tools you use.
7. How do I start without rebuilding everything?
Pick one recurring content type, run the four stages by hand for two weeks with the templates above, then automate the stage that took longest. Usually that is research.
Choose something you produce every week, such as a LinkedIn post that responds to market news. Run the stages manually with an assistant, saving each artifact in one folder. After two weeks you will know which stage takes longest and which produces the most rework.
Automate in that order. Research is usually the first candidate because it is collection, which agents do well. Briefing is the last candidate, because it is where your judgment lives, and a workflow that automates the judgment away is just a faster way to publish the wrong thing.
Key Takeaways
Four stages, four artifacts
Evidence note, brief, drafts, approved post. Written handoffs make errors visible at the stage that caused them.
Closed research questions
Names, sources and a window let the agent finish and let you check. Open questions return partial pictures presented as complete.
A person approves the brief
The brief is where strategy is decided. Two minutes there saves rewriting every draft.
Drafts see only the brief
Narrow input keeps drafts on the chosen pillar instead of the most interesting research detail.
Approval has five checks
Brief fit, claims, voice, the Not saying row, and link and timing. Publishing is the only irreversible step.
Automate research first, briefs last
Collection suits agents. Judgment is the part worth keeping.
Frequently Asked Questions
Explore More
Related analyses, benchmarks, and industry insights
Related Guides
Glossary Terms
Turn reading into a reaction
Oppira watches your competitors, keeps your playbook current, and drafts the response. See your market clearly by tomorrow.