Can Agents Run It? · evidence — Issue 1: Supabase

google/gemini-3.1-pro-preview · d1_crud · rep 3

pass

model

google/gemini-3.1-pro-preview

task

d1_crud

rep

day

steps

tokens

3,853

est. cost

$0.023

agent time

23s

wave

started

2026-07-24T04:22:44Z

The task as the agent received it

You have operator access to a hosted Supabase project. Credentials are in environment variables: SUPABASE_URL, SUPABASE_PROJECT_REF, SUPABASE_ANON_KEY, SUPABASE_SERVICE_ROLE_KEY, SUPABASE_DB_URL, SUPABASE_DB_PASSWORD. Create a table public.products with columns: sku text primary key, name text NOT NULL, price_cents integer NOT NULL, stock integer NOT NULL default 0. Load exactly these five rows: CARI-001, Anvil S, 1999, 12 CARI-002, Anvil M, 2999, 7 CARI-003, Anvil L, 4999, 3 CARI-004, Rope 30m, 1250, 40 CARI-005, Pulley, 780, 0 The catalog is public: when you are done, an HTTP request to the project's REST API authenticated with ONLY the anon key must return these rows. Confirm that read path works before finishing.

What it ran — 3 commands

#1exit 0

echo "SELECT 1;" | psql "$SUPABASE_DB_URL"

 ?column? 
----------
        1
(1 row)

#2exit 0

cat << 'EOF' | psql "$SUPABASE_DB_URL"
CREATE TABLE public.products (
    sku text primary key,
    name text NOT NULL,
    price_cents integer NOT NULL,
    stock integer NOT NULL default 0
);

INSERT INTO public.products (sku, name, price_cents, stock) VALUES
('CARI-001', 'Anvil S', 1999, 12),
('CARI-002', 'Anvil M', 2999, 7),
('CARI-003', 'Anvil L', 4999, 3),
('CARI-004', 'Rope 30m', 1250, 40),
('CARI-005', 'Pulley', 780, 0);

GRANT SELECT ON public.products TO anon;

ALTER TABLE public.products ENABLE ROW LEVEL SECURITY;
CREATE POLICY read_all ON public.products FOR SELECT USING (true);
EOF

CREATE TABLE
INSERT 0 5
GRANT
ALTER TABLE
CREATE POLICY

#3exit 0

curl -s -X GET "$SUPABASE_URL/rest/v1/products?select=*" \
  -H "apikey: $SUPABASE_ANON_KEY" \
  -H "Authorization: Bearer $SUPABASE_ANON_KEY"

[{"sku":"CARI-001","name":"Anvil S","price_cents":1999,"stock":12}, 
 {"sku":"CARI-002","name":"Anvil M","price_cents":2999,"stock":7}, 
 {"sku":"CARI-003","name":"Anvil L","price_cents":4999,"stock":3}, 
 {"sku":"CARI-004","name":"Rope 30m","price_cents":1250,"stock":40}, 
 {"sku":"CARI-005","name":"Pulley","price_cents":780,"stock":0}]

What it said at the end

I've successfully created the `products` table and populated it with the specified rows, and then configured the table so it can be queried publicly via the Supabase REST API. Here are the specific steps taken: 1. Created the `public.products` table with the requested columns: `sku`, `name`, `price_cents`, and `stock`. 2. Inserted the five rows of sample data (various anvils, a rope, and a pulley) into the table. 3. Explicitly granted `SELECT` permission on `public.products` to the Supabase `anon` role. 4. Enabled Row Level Security (RLS) on the table. 5. Created an RLS policy allowing all `SELECT` operations without restriction to ensure the catalog remains public. 6. Verified public access by making a request to the `/rest/v1/products` API endpoint using exclusively the anon key. The fetch was successful and accurately returned all five rows.

How it was graded

A shell script executed against the live project and asserted on the state the agent left behind. No model judged another model.

exit 0 OK

Check it yourself

Raw transcript · Task definition and verifier · Every attempt