Research

Content Intelligence Agent

Reads a competitor's content for what they claim, evidence, and avoid

Version 3Published Sep 2, 2026
Watch it work▶ Try it on your own figures — free

6 of 8 watched sources need attention.

8 watched sources checked. 6 flagged. The largest gap is 107 days.

Start with Pricing page. Northwind has the most flagged.

What a change means for you is for your team to read; the list only shows which sources are stale or unread.

6
6/8
Flagged
6
8
Flagged
6
Longest (days)
107
Share flagged
75%

Why rows were flagged

6
  • Not checked for 30 days43%
  • Changed and not reviewed43%
  • Never checked14%

Value flagged by Rival

  • Northwind2
  • Swiftline2
  • Pixel Lab1
  • Harbour1

Items to act on, worst first

ItemRivalValueDays since the last checkWhy
Pricing pagePixel Lab181Not checked for 30 days, Changed and not reviewed
Pricing pageNorthwind10Changed and not reviewed
Feature pageHarbour10Never checked
Partner pageSwiftline10Changed and not reviewed
Security pageSwiftline1107Not checked for 30 days
Careers pageNorthwind160Not checked for 30 days

What to do this week

  • Resolve Pricing page first: it is the most urgent on the list.
  • Fix the data or the status on every flagged row, then re-run.
  • Re-run this check every time the list changes, before it reaches a decision.

Do

  • Fix the highest-risk item first, then run the check again on fresh data.

Don't

  • Don't act on one row alone: open the source record first.

How to improve

  • Add more detail per row (owner, date, source) so the next report can trace each item.
  • Add a second period of data so the next report can show whether things are improving.

Demo

Try it now — free

Type your figures (or fill in samples) and get the answer in a minute.

Start from a template

Make it decision-ready

Also include

No card · no API key · your figures are not stored

Overview

Summarising a competitor's content is easy and nearly useless. What matters is narrower: what they are claiming, which of it they actually evidence, who they are speaking to, and what they never mention.

This reads the material you supply — an article, a talk transcript, a launch post, a stack of them — and reports positioning rather than plot. Which claims carry a number, a customer or a study behind them, and which are asserted. Which audience the language is written for. Where their story changed between one piece and the next.

And it reads for absence, which no summariser does. A rival who never mentions price, never names a customer, or meets every integration question with "coming soon" has told you something specific. Silence is only visible when you go looking for it, and it is usually the most actionable thing in the pile.

Benefits

Positioning in an hour

Instead of a week of reading nobody schedules.

Their weak claims, named

The unevidenced ones are where your own evidence wins.

The gaps you can take

What they avoid is often what they cannot do.

What it does

  • Reads for absence

    What they consistently never mention. No summariser produces this, and it is usually the most useful finding.

  • Separates claimed from evidenced

    Which assertions carry a number, a customer or a study — and which are just said confidently.

  • Identifies who it is written for

    The vocabulary, the objections handled, the assumed budget. Positioning shows in the language.

  • Tracks the story changing

    Where their message shifted between pieces. A change of story is a change of strategy.

  • Quotes rather than characterises

    Every finding carries the line it came from, so you can judge it yourself.

  • Repeats no allegation

    It reports what they published about themselves, not what anyone says about them.

What this changes

What this changes about your week

It takes over
Reading everything a competitor published to work out what they are actually claiming.
Done today by
Whoever has an afternoon, which is nobody.
How often
Every launch, every quarter, every new market.
Typical manual effort
Reading a rival's last quarter properly is a day.

Why Research in particular. Summaries of a competitor's content are useless. What matters is which claims they evidence and what they never mention — and absence only shows up when something goes looking for it.

  • Runs unattended

    Started by you or by an event, and it finishes on its own. Nothing waits for someone to be at a desk.

  • The same standard every time

    The two-hundredth item is held to the bar the first one was. Consistency is the part people cannot sustain.

  • It cannot act on its own

    Content Intelligence Agent has no path to sending, spending or committing. That limit is why its output is safe to act on.

How it runs

This agent runs server-side through the PROMIVO runtime. Each run is logged step by step and every tool call is permission-checked before it executes.

  1. 1InputValidated against the agent input schema
  2. 2Modelclaude-opus-5 with automatic fallback
  3. 3Toolsfetch_web_page, extract_structured_data
  4. 4PermissionsRuns READ actions automatically; anything higher waits for approval
  5. 5OutputStructured result matching the output schema
  6. 6LoggingTokens, duration and every step recorded

Requirements

Integrations

No integrations required.

Before you start

  • The content — articles, transcripts, posts
  • What you sell, so gaps can be judged against it
  • Requires the All-Access plan or higher

Use cases

A competitor's launch

What actually changed in their positioning, not their wording.

Entering a market

How incumbents talk, and to whom.

Sharpening your own message

Where every rival is saying the same unevidenced thing.

Pricing

All-Access

Billed monthly through your PROMIVO subscription. Cancel at any time.

Runs consume your plan allowance for agent executions and tokens. See plan limits

FAQ

Can it read a video?

It reads a transcript. Supply one and it works from what was said; it does not watch video and will not pretend to have seen something it read.

Will it tell me their strategy?

It reports what their published material shows and what it avoids. Inferring intent from marketing copy is guesswork dressed as insight, and it says so rather than doing it.

Does it use reviews or rumours?

No. It reads what a company published about itself. Repeating an allegation about a competitor is a risk to you, not to them.

Reviews

Reviews open once customers have run this agent.

Need this agent to work differently?

Tell us what to change and our team will scope a customised version for your business.

Customize this agent