Record the decision when you make it. Review it when it matters.
Research Decision Journal is a structured workspace for your consequential research decisions — what you chose, what you considered, your reasoning, your assumptions, and what you expected to happen. Months later it resurfaces each decision for review, and across many decisions your own calibration becomes visible.
Your decisions are stored in your browser. No AI reads them; nothing is uploaded.
The decisions that shaped your research are the ones you forget
Which methodology? What inclusion criteria? When to abandon a line of inquiry, and when to persist? You weighed real alternatives and had real reasons — but a year later, hindsight has quietly rewritten the story, and you can no longer reconstruct what you actually believed at the time.
- Hindsight bias is undefeated. Once you know how it turned out, you cannot honestly recall how uncertain you were going in.
- Your reasoning is never written down. So you can't defend it later, can't learn from it, and can't see your own patterns.
- The defense asks "why did you do it this way?" — and a contemporaneous record beats a reconstructed rationalisation every time.
A 30-year practice, imported into research
How it works
Capture the decision
Pick one of 13 templates, then record the decision, the alternatives, your reasoning and assumptions, and what you expect to happen — with a confidence level.
Review on schedule
The journal resurfaces each decision at set intervals. An amber badge on the toolbar icon shows how many reviews are due. You record what actually happened.
See your calibration
Across many reviewed decisions, deterministic metrics — computed from your own coded outcomes — show how well-calibrated your confidence really is.
What's inside
13 curated decision templates
Research-design, execution, and strategic decisions — each with scholarly grounding, capture prompts, review prompts for every interval, and a worked example. The catalog is the IP, and it's the same for everyone.
Five timed review intervals
30 days, 3, 6 and 12 months, and a thesis-completion review you set yourself. Status moves from pending to overdue to completed automatically — no manual marking.
Calibration & portfolio analytics
Crisp predictions get rigorous calibration; outcome assessments get an honest, approximate metric — shown separately, never blended. Plus decision-type distribution and recurring-assumption analysis.
Defended-Decisions Document
Export a long-form Markdown synthesis of your reviewed decisions — built for thesis methodology appendices and defense preparation.
No nagging
Reviews surface when you open the extension — there are no emails, push notifications, or calendar syncs. The discipline of opening the journal is part of the practice.
No AI, on purpose
Nothing here judges your reasoning, suggests alternatives, or auto-codes outcomes. You do the thinking; the tool provides the structure and the deterministic maths.
Privacy & Trust
- Your decisions never leave your machine. Everything you write — decisions, reasoning, assumptions, reviews, internal notes — lives in
chrome.storage.localon your device. - No AI runtime, no telemetry, no analytics, no account. The extension does not read any web page and runs no inference on your content.
- One optional network call, only if you ask for it. If you enter an email and click Subscribe for product updates, only that email address is sent to GradSummit's sign-up service — never any decision content.
- Internal notes are never exported. The private "internal note" field on every decision and review is excluded from every export by design.
It is a workspace for structured decision recording — not an AI coach, and not a reminder app. Read the full privacy policy.
Built by Dr. Rafiq Muhammad, PhD — author of the Mastering Research book series.
Pricing
Every feature, for everyone — no subscription, no tiers, no account.
All 13 templates, all five review intervals, calibration and portfolio analytics, and every export are unlocked.
Email is entirely optional and opt-in — leave it blank forever, or add it to hear about occasional updates.
Frequently asked questions
Does an AI evaluate my decisions?
No — and deliberately so. There is no AI runtime anywhere in this tool. It does not judge your reasoning, suggest alternatives, code your outcomes, or generate review prompts. You make the decisions and code the outcomes; the tool provides the curated structure and computes deterministic metrics from what you enter. "Decision journal" here means a workspace, not a coach.
Will it remind me by email, push, or calendar?
No. Reviews surface inside the extension when you open it, with an amber badge on the toolbar icon showing how many are overdue. There are no emails, notifications, or calendar syncs. This is intentional: the discipline of opening the journal is part of the practice. If push or calendar reminders are essential to your workflow, this isn't the right tool.
Is my decision content uploaded anywhere?
No. Every decision, review, assumption and note stays in chrome.storage.local on your device. The only thing the extension can send to GradSummit is your email address — and only if you explicitly opt in to product updates and click Subscribe. No decision content is ever transmitted. See the full privacy policy.
How much does it cost?
It's free, with no subscription and no paid tiers. Every feature is available to everyone. There's nothing to buy and no account to create.
What does "calibration" actually measure?
When you record a decision you give your expected outcome a confidence level, in one of two formats. Crisp predictions (a specific, checkable claim) get rigorous calibration. Outcome assessments (a softer match-to-expected coding) get an honest but approximate metric. The two are tracked and shown separately, never blended — and both are computed deterministically from outcomes you code yourself.
What are the 13 templates?
They span research-design decisions (research question, methodology, theoretical framework, inclusion/exclusion), execution decisions (sample size, statistical analysis, scope, resource allocation), and strategic decisions (abandon-vs-persist, pivot-vs-stay, collaboration, publication) — plus a generic template for anything else. Each ships with scholarly grounding, capture and review prompts, and a worked example.
Can I get my data out?
Yes. You can export a full JSON backup at any time and re-import it, and you can export single decisions, your whole library, the portfolio analytics, and the long-form Defended-Decisions Document as Markdown. One click in settings clears everything from your device.
What if I find a bug?
Email support@gradsummit.com — replies go to a real human (the developer).