Agents / Consumer Agent

Which consumers should we act on – and who’s about to leave?

The Consumer Agent turns the opportunity into people. It reads purchase behavior in your CRM and loyalty data together with what consumer research says those people need, so you know who to target, what they are looking for, who is drifting away and what to offer each of them.

Works on its own or as part of the chain – guided step by step, or autonomously.

Picked up from the Demand agent
Picked up from the Demand Agent

The case so far

The Demand Agent found that reduced-sugar premium dark chocolate grows fastest exactly where our share is lowest, and sized it at CHF 6.8M in sales and CHF 2.1M in margin. It handed over the opportunity – and three questions for the Consumer Agent.

Most of the time
Propensity models in the CRM say who is likely to buy. They don’t say why, or what would make the product right for them. The research that knows sits in another team’s deck.
With the Consumer Agent
Behaviour from the CRM and needs from research, linked through shared segments. Every audience comes with the job it wants done and the message that fits, and goes to your CRM or campaign system with its campaign brief.
Three steps · one example

You ask in plain words. The agent plans, you approve, it answers.

Each step is one question to the Consumer Agent. The answer comes back validated, with weak evidence flagged and outputs ready for your systems.

Shown step by step – it can also run on its own. The case below is guided: one question per step, with suggested prompts leading to the next. Give the Consumer Agent a broader brief and it works autonomously – it plans the analysis itself, goes as deep as the question needs, skips steps that add nothing and comes back with the answer and its full audit trail.

Consumer agent - Segmentation
Step 1

Segmentation

Behavioural and attitudinal segments, built on research fused with real purchase behaviour – not just who is likely to buy, but what they are trying to get done.

Other questions it answers
  • “Which loyalty members look like the ‘quality gifters’ in our U&A study?”
  • “Who buys the category but not us – and why not?”
  • “Which group drives the growth in oat drinks, and what do they care about?”
Consumer agent - Churn & retention
Step 2

Churn & retention

Churn risk scored per consumer, with the reason behind it and the window in which a contact still works. Two people can leave for opposite reasons; the agent separates them so neither gets the wrong fix.

Other questions it answers
  • “Which high-value subscribers are about to downgrade, and what triggers it?”
  • “Who stopped buying after the price increase, and who left for another reason?”
  • “How many of our at-risk members can we actually contact?”
Consumer agent - Next best offer
Step 3

Next best offer

Offer, channel and message calibrated per segment on what each group responds to. Discounts go only where they change behaviour.

Other questions it answers
  • “Which customers will buy at full price without a coupon?”
  • “What should a new app user be offered after the first order?”
  • “Which channel reaches lapsed members who no longer open email?”
Target segments land in your CRM – ready to run.
Activate directly

Target segments land in your CRM – ready to run.

The moment a segment is approved, it is pushed to your CRM or CDP as a live audience, with the offer, the channel and a control group already set. Your campaign team runs it; the lift is measured from day one.

Target segments land in your CRM – ready to run.

Shown in this case
Segmentation
Churn & retention
Next best offer
Examples we tune or build per client
+ Research-to-CRM lookalikes
+ Consent & reach
+ Campaign lift measurement
Inside the Consumer Agent

A family of sub-agents, tuned to you

The three steps above are run by specialised sub-agents. We tune them to your categories, data and ways of working – and build new ones when your teams need them.

The Consumer agent hands over to the Sales agent
Or hand it on

The Consumer Agent hands over to the Sales Agent.

It carries the context across and suggests the next three questions. Run them, and the Sales Agent picks up exactly where this one left off.

What you get

Every recommendation is computed by statistics and machine learning, validated, and traceable to the data cell it came from. The language model picks the variables and writes the explanation; it does not calculate the numbers.

Segments that combine behaviour from your CRM with needs from your research
A campaign brief per audience: offer, message, channel and timing
Target audiences that go straight into your CRM, CDP, activation and campaign systems
A control group designed in, so the lift is measured

Numbers from live deployments

Example
Retention plan for a regional retailer
+27%
average basket size
−27 pp
customer churn
3×
faster campaign build

Bring your toughest question. Watch the Consumer Agent answer it.

A 30-minute live session on prepared data: the agent interprets your question, runs the analysis and returns a validated answer you can drill down to the data cell.