Growth research and analysis
Digs into a growth question until there's an answer with evidence behind it. It makes the question answerable first — which step, which segment, which source — then checks the boring explanations like broken tracking or an ended campaign before reaching for behavioural theories. You get the finding, the numbers supporting it, and an honest confidence level.
Published by Oasis Platform · Free to add
Connect these once. Oasis holds the connection, and every agent you build after this can reuse it.
OpenAI AgentsIt lands in your Oasis
Growth Researcher is created in your workspace with its instructions and settings already filled in.
You connect its apps
Sign in to PostHog and Mixpanel once and it has everything it needs.
You make it yours
Rewrite the instructions, swap the model, add files and skills. It is a starting point, not a lock-in.
Answers questions from your warehouse or your spreadsheets. It learns the schema and confirms ambiguous definitions before querying, then sanity-checks the result — row counts, reconciliation, fan-out from a bad join — because wrong-but-plausible numbers are the real risk here. You get the answer in one sentence, then the number, then the caveats, with the query shown.
Oasis PlatformResearchTells you what's genuinely moving in your space and what's just a news cycle. One loud announcement isn't a trend; the same behaviour showing up in three unconnected places is, and it reports the difference. If nothing really changed this week it says so rather than manufacturing three trends.
Oasis PlatformResearchTakes a pile of sources — papers, reports, transcripts, interviews — and produces the synthesis rather than a reading list. It organises by theme, shows where sources agree and whether they're genuinely independent or just citing each other, and never resolves a real conflict by averaging. It ends with the questions the evidence leaves open.
Oasis PlatformResearchAnswers product questions from your PostHog data — funnels, retention, feature adoption, cohort comparisons. It verifies the events mean what you think before analysing, because a funnel built on a renamed event produces a confident wrong answer. Every finding comes with sample sizes and the segment breakdown, since a flat overall metric routinely hides one segment collapsing.
Oasis PlatformResearchAdd it to your Oasis, connect its apps, and hand it the first task. Everything about it stays editable.
© 2026 Oasis, Inc.
Add to your Oasis