Describe the job.
Keep it running.

One product, from your first brief to a dataset that stays current. Jsonify builds the pipeline, runs it and repairs it when a source changes.

01 / Describe

Start with the data you need.

Tell Jsonify what to collect, which sources matter and how often it should refresh. A product catalogue, a menu tracker or a property listing feed: the brief defines the job.

factory.jsonify.comIllustration
Retail intelligence / New pipeline
Track grocery prices and stock across three retailers. Refresh every morning.
Jason

I’ll keep the product, pack size, price and availability together, with a link back to each source.

3 sources inspected
Product fields identified
Daily refresh proposed
Ask Jason to refine the brief
Setup and pipeline brief · Illustrative product preview

02 / Build

Your brief becomes a pipeline.

Jsonify builds the steps that collect, process and verify your data. Follow the pipeline diagram and version history; ask Jason when you want to change the sources, fields or schedule.

factory.jsonify.comIllustration
Retail intelligence / Retail prices

Retail prices

Ready to run
OverviewStepsRun historyv24
01 / SourcesRetailer list3 public websites
02 / CollectFetch productsHTML → structured fields
03 / ProcessNormalize pricesCurrency · pack sizes
04 / PublishRetail pricesChecked dataset
Pipeline built · 4 steps · Revision v24 Ask Jason to make a change
Pipeline diagram and version history · Illustrative product preview

03 / Run

Run once. Then keep it current.

Run your pipeline and refresh it on a schedule. Collection workers handle the sources in parallel, while run history records what happened each time.

factory.jsonify.comIllustration
Retail intelligence / Retail prices

Run history

Daily · 06:00
Collecting product pages Run #184 · v24
2,164 / 2,840
Worker 1 · Retailer AWorker 2 · Retailer BWorker 3 · Retailer C
RunStatusRowsDuration
Today · 06:00Running2,1641m 42s
Yesterday · 06:00Completed2,8402m 18s
Monday · 06:00Completed2,8122m 09s
Scheduled runs and worker activity · Illustrative product preview

04 / Verify

Check the rows before they arrive.

Check types, missing values and duplicates before publishing. Keep source context alongside each result so your team can trace and compare the data.

factory.jsonify.comIllustration
Retail intelligence / Retail prices

Validation results

Checks complete
TypesPrice fields are numeric
NullsRequired fields present
DuplicatesUnique product + source
2,840 rows published12 rows held for review
ProductPriceSourceResult
Oat drink · 1L£2.20Retailer A✓ Passed
Coffee · 250g£4.80Retailer B✓ Passed
Green tea · 80 bagsRetailer CMissing price
Validation results and published dataset · Illustrative product preview

05 / Deliver

Use the data where you work.

Sheets or Excel, refreshed on schedule. Snowflake, S3, Postgres and webhooks. Slack and Teams alerts. ChatGPT, Claude or Cursor over MCP. Or an automatic insights dashboard on a share link.

factory.jsonify.comIllustration
Retail intelligence / Retail prices

Connections

After each verified run

Google SheetsMarket watch / Retail prices

Updated

SnowflakeINTELLIGENCE.PUBLIC.RETAIL_PRICES

Synced

Team alertsNotify when a price changes

Connected

Your agent · MCPThe same dataset in your conversation

Available
2,840 checked rows · Delivered at 06:03
Dataset delivery settings · Illustrative product preview

06 / Repair

A source changes. The pipeline adapts.

Jsonify diagnoses extraction failures, repairs the code and verifies the change before activating a new revision. Run history records what changed and whether the repair passed its checks. When a repair needs human attention, the issue remains available to review.

factory.jsonify.comIllustration
Retail intelligence / Retail prices

Repair history

Recovered

Source change detectedRetailer B changed its product-page layout.

Collection step repairedPrice extraction updated. Revision v23 → v24.

Verification passedTypes, nulls and duplicates checked on 50 sample rows.

Run resumed2,840 checked rows published to your destinations.

Jason The price field moved. I updated the collection step and verified the repair.

Repair summary, verification and resumed run · Illustrative product preview

One product. Two kinds of collection.

Radar monitors what’s published. Benchmark submits a scenario and collects the offer.

RadarNow available

Monitor what’s published.

Collect prices, menus, listings and availability from websites and apps. Follow what changes across sources and markets.

BenchmarkEnterprise

Compare what’s offered.

Run defined scenarios through forms to collect comparable insurance quotes, rental rates and personalised offers.

Build a dataset that keeps working.

Describe the data you need. Build for free with 100 rows a month, no credit card required.

Connect your data assistant

Build datasets and work with your data in ChatGPT, Claude, Teams or another assistant.

Connect in ChatGPT

  1. Open Settings → Security and login and enable Developer mode.
  2. Open Plugins and select + to create a connection. Name it Jsonify, add a short description, and paste the URL below.
  3. Use OAuth for authentication, select Create, and sign in to your Jsonify account when prompted.
  4. Start a new chat and select Jsonify from + → More, then describe your dataset.
Server URLhttps://factory.jsonify.com/mcp

If Developer mode is unavailable, your plan or workspace settings may restrict custom connections.

Official ChatGPT setup guide ↗

Then say: “build me a dataset of competitor product prices and availability, refreshed daily”. Full instructions per client on /connect.