Ask whether the right thing is tracked
An installed analytics tool does not guarantee that the event taxonomy can answer the product question.
How it works
From one question to a learning loop.
Sightspool begins with the uncertainty the team is carrying—not with a dashboard or a preselected research method. It connects what is known, routes what is missing and keeps the decision alive after the change ships.
The complete loop
Sightspool carries the work past the finding.
Research is a stage when the evidence requires it. A recommendation is useful only when it changes an owned action and the team later learns from the result.
- 01
Frame the question
The team states what it is trying to understand, why it matters now, who owns the decision and what a useful answer must change.
- 02
Connect the context
Sightspool brings together approved behavioural, commercial, customer and product sources, with provenance and limitations visible.
- 03
Validate the signal
The system checks that the event or evidence exists, the measure matches the question and the sample is sufficient before treating it as a read.
- 04
Route the investigation
The agent selects the relevant research, interaction-design and service-design lenses, and reads through them in parallel when the question crosses disciplines.
- 05
Recommend and decide
The agent produces a recommendation, confidence, downside and next move. A senior human enters where necessary; the client makes the final call.
- 06
Watch and learn
The action receives an intended outcome and review window. After implementation, the observed, null or negative result updates the customer’s context.
PostHog and the evidence layer
Analytics is a sensor. Sightspool operates around it.
Sightspool does not rebuild session replay, funnels, dashboards or surveys. It uses those sources to answer a different question: what does the UX function need to understand and do next?
Keep unknown different from zero
A missing event, a measured zero and an insufficient sample lead to different decisions and remain different product states.
Join behaviour to context
Behaviour becomes more useful when the agent can relate it to customer intent, account structure, revenue and what changed in the product.
Turn the read into an action
Sightspool routes the evidence through the appropriate UX discipline and preserves the recommendation, downside, decision and outcome.
Where humans enter
Escalation is part of the system, not a failure of it.
Sightspool concentrates human attention on work where consequence, ambiguity, participant safety or professional responsibility justifies it.
Senior review
A consequential recommendation needs a practitioner to examine the evidence, logic, limitation and downside.
Sensitive research
Participant safety, difficult topics and high-risk recruitment or interpretation remain deliberately human-led.
Unresolved tension
When the lenses disagree and the evidence cannot settle it, the system records the tension and escalates rather than bluffing.
It becomes a record
Each escalation opens one auditable event carrying what triggered it and why, so “a human looked at it” is a fact with a timestamp rather than a reassurance.
It reaches a named person
The event is assigned to a senior practitioner, who is notified, works it from a real queue and records the minutes it actually took.
You pick the path
Handle it in-house, measure it, commission the practitioner or dismiss it with a reason. Your choice is recorded, and it stays your choice.
Their judgement is scored
When measurement later settles the same question, the practitioner’s read is graded against it. Seniority is a claim; accuracy is a record.
!
The client still decides.Sightspool and its senior practitioners advise on customer and experience uncertainty. They cannot rule a verdict or approve an action on your product — the authorised product leader owns the final decision, roadmap and delivery.
Being honest about time
What you get on day one, and what needs traffic.
A measured verdict needs a sample. If your product is early, the register will honestly say “still gathering” for a while — so here is the real sequence, rather than a promise that quietly fails to arrive.
Day one · what is assumed
Your repo and product surfaces become a written register of the assumptions you are already betting on. Most teams have never seen theirs listed. This needs no traffic and no account.
Week one · a senior read
The agent and, where it matters, a senior practitioner give a qualitative read on the assumptions that carry the most risk. That is evidence and it is labelled as evidence — never dressed up as a measurement.
When you have traffic · the verdict
Once an assumption's signal clears its minimum sample, it gets measured against the threshold you set in advance. Until then it reads “still gathering, n of min_n” — which is the honest answer, not a broken one.
Start with a real question
Start with the uncertainty your team keeps carrying.
Bring one real product question. Sightspool will not ask you to pretend your current data is cleaner than it is — it will tell you what it can and cannot answer with what you have today.