Test siift as a real user from login through active project use coming in fresh from website, on desktop.
The goal is to uncover obvious functional, UX, AI, and reliability issues across the full experience rather than test individual features in isolation.
Approach the test naturally: use a real or hypothetical business idea and try to make meaningful progress with it.
Test Flow
1. 1. Sign-in & Project Setup
2. Workspace / Dashboard Works
3. Work Through the Project
4. Files, Data & Connections
5. Actions & Interactive Features
6. UI / UX / Reliability Issues
7. AI Agent Issues
3. Files, Data & Connections
Bug Reporting
For every issue, capture:
Title: Short description of the problem
Severity: Critical / High / Medium / Low
Location: Page, phase, feature, or workflow
Steps to reproduce: What you did immediately before the issue
Expected: What should have happened
Actual: What happened instead
Evidence: Screenshot or screen recording where useful
Reproducible?: Always / Sometimes / Once
Pay particular attention to issues that can be reproduced consistently.
Definition of Done
The test is complete once you have:
Created and actively used a new project
Progressed through several phases/workflows
Had meaningful multi-turn conversations with the AI
Added structured ideas/research
Uploaded files
Tested available integrations
Used suggestions and agent/action runs
Used the Action Board and created tasks
Returned to earlier parts of the project to test persistence/context
Documented every meaningful bug, failure, stall, or clearly incorrect AI behavior encountered
Send video evidence for every issue in the accepted tester chat.
Record your screen and microphone audio for the full test. Narrate your actions, every error you find, and anything confusing, poor, or worth improving.
Attach the narrated video as an MP4, MOV, or WebM no larger than 512 MB, plus at least one representative screenshot.
For each issue include a short title, a severity (critical/high/medium/low), and exact steps to reproduce.
Submissions are reviewed automatically. $10.00 is released per accepted submission.
Tester requirements:
25-45 years old
Has a business Idea
Strong computer skills
Familiar with AI apps like ChatGPT or Claude
What you must do to be paid
Before you apply
Access to a device that can open https://siift.ai/
# siift Desktop Web App E2E QA Test
## Objective
Test siift as a real user from login through active project use coming in fresh from website, on desktop.
The goal is to uncover **obvious functional, UX, AI, and reliability issues** across the full experience rather than test individual features in isolation.
Approach the test naturally: use a real or hypothetical business idea and try to make meaningful progress with it.
## Test Flow
### 1. 1. Sign-in & Project Setup
### 2. Workspace / Dashboard Works
### 3. Work Through the Project
### 4. Files, Data & Connections
### 5. Actions & Interactive Features
### 6. UI / UX / Reliability Issues
### 7. AI Agent Issues
### 3. Files, Data & Connections
## Bug Reporting
For every issue, capture:
**Title:** Short description of the problem
**Severity:** Critical / High / Medium / Low
**Location:** Page, phase, feature, or workflow
**Steps to reproduce:** What you did immediately before the issue
**Expected:** What should have happened
**Actual:** What happened instead
**Evidence:** Screenshot or screen recording where useful
**Reproducible?:** Always / Sometimes / Once
Pay particular attention to issues that can be reproduced consistently.
## Definition of Done
The test is complete once you have:
* Created and actively used a new project
* Progressed through several phases/workflows
* Had meaningful multi-turn conversations with the AI
* Added structured ideas/research
* Uploaded files
* Tested available integrations
* Used suggestions and agent/action runs
* Used the Action Board and created tasks
* Returned to earlier parts of the project to test persistence/context
* Documented every meaningful bug, failure, stall, or clearly incorrect AI behavior encountered
Submission requirements
Video assignments require spoken microphone narration throughout. Captions, written narration, and on-screen text are not substitutes.
11. Sign-in & Project Setup* [ ] Log into siift from the website via both paths on desktop - input new idea box, and sign in button,
* [ ] Create a new project
* [ ] Confirm the project loads correctly and information persists with not blockers or hiccups
22. Workspace / Dashboard WorksExamples include:
* Buttons do nothing
* can't create a new project
* Projects saved don't show fails to save
* Pages or components fail to load
* Incorrect information appears on profile (name, email, saved personalization data)
* Account doesn't start with some free credits when signed up
* Account credits don't reduce as you work through project with Ai Agent
* Tutorials don't play when opened from dashboard nav bar
* Pricing page doesn't show when clicked on nav bar button
* feedback form can't submit
33. Work Through the ProjectWork through **at least the first several relevant phases** of the project.
* [ ] Add and develop business ideas
* [ ] Ask siift questions and have several back-and-forth conversations
* [ ] Follow recommendations or next-step suggestions
* [ ] Navigate between project phases
* [ ] Add, edit, and review information in the structured workspace
* [ ] Add ideas and research/evidence to the relevant tables
* [ ] Revisit previously entered information and confirm it remains accurate
Do not follow a rigid script.
44. Files, Data & Connections* [ ] Upload one or more files
* [ ] Confirm siift correctly recognizes and uses information from those files
* [ ] Connect at least one available external tool/data source, where possible
* [ ] Ask questions that require siift to use the connected information
* [ ] Confirm connected information appears to be incorporated correctly
55. Actions & Interactive FeaturesUse the main interactive functionality you encounter, including:
* [ ] Suggestions/recommended prompts
* [ ] Action buttons / action runs
* [ ] Add-to-table or similar structured-data actions
* [ ] Research-related actions
* [ ] Buttons generated within conversations
* [ ] Navigation and phase controls
* [ ] Any edit/delete/update controls encountered
Action Board features:
* [ ] Open the Action Board
* [ ] Create several tasks
* [ ] Edit/update tasks
* [ ] Change task status where supported
* [ ] Confirm tasks persist correctly
* [ ] Navigate away and return to confirm the board remains accurate
Check that every interaction produces the expected result and does not leave the UI in an unclear state.
66. UI / UX or Reliability IssuesFlag anything that makes you think:
> "I don't know what happened, what I'm supposed to do next, or whether this worked."
This includes confusing states, unclear feedback, unusually slow responses, broken formatting, unexpected redirects, disappearing information, or workflows that technically work but feel obviously broken. Buggy graphics or images and components as well.
77. AI Agent IssuesAlso treat poor AI behavior as a QA issue, including:
* AI ignores instructions or important project context
* AI appears unaware of information already provided
* AI repeatedly asks for information it already has
* Previous chat messages/context appear to be lost or improperly managed
* Responses contradict known project information
* Suggestions are unrelated to the user's current goal
* Agent starts an action but never completes it
* Agent hangs, stalls, or remains in a loading state
* Tool/action runs silently fail
* AI claims an action occurred when it did not
* Information added through chat does not correctly propagate to the structured workspace
* Changes in the structured workspace are not reflected in later AI responses
8Complete the assigned test stepsFollow every instruction above. If a step is blocked, name the exact step and explain what prevented it.
9Describe test coverageList the steps, pages, controls, devices, and paths you actually tested.
10Report concrete resultsExplain what happened, what worked, and any confusing or poor experience you observed.
11Provide the required video evidenceAttach an MP4, MOV, or WebM screen recording no larger than 512 MB, plus at least one representative screenshot. Speak your findings aloud while recording whenever you can: narration is strongly encouraged and makes your report far more useful, but it is not required and a quiet recording will still be reviewed on its merits.
12Map every attachment to the reportIn the same chat message as each upload, explain what every attached file shows and which tested step or finding it supports.
13Make every issue reproducibleFor each issue, include a short title, severity, expected behavior, actual behavior, and exact reproduction steps.
14Still report useful observations if nothing failedA no-issue result must still say exactly what you tested and include concrete usability observations.
REQUIREMENTS
•
Access to a device that can open the target URL
•
Report every issue with a severity and exact reproduction steps
•
Only submit evidence you captured yourself during this run
•
25-45 years old
•
Has a business Idea
•
Strong computer skills
•
Familiar with AI apps like ChatGPT or Claude
SKILLS NEEDED
25-45 years oldHas a business IdeaStrong computer skillsFamiliar with AI apps like ChatGPT or Claude