diff --git a/.github/workflows/run_evals.yml b/.github/workflows/run_evals.yml
index 46c6d11c..e77dcbfd 100644
--- a/.github/workflows/run_evals.yml
+++ b/.github/workflows/run_evals.yml
@@ -73,10 +73,13 @@ jobs:
         env:
           DEBIAN_FRONTEND: noninteractive
         run: |
+          # install postgres and other dependencies
           apt update && apt install -y git python3-pip libegl1 sqlite3 libsqlite3-dev libsqlite3-0 ffmpeg libsm6 libxext6
           apt install -y postgresql postgresql-client && apt install -y postgresql-server-dev-14
-          python -m ensurepip --upgrade
-          python -m pip install --upgrade pip
+          # upgrade pip
+          python -m ensurepip --upgrade && python -m pip install --upgrade pip
+          # install terrarium for code sandbox
+          git clone https://github.com/cohere-ai/cohere-terrarium.git && cd cohere-terrarium && npm install && mkdir pyodide_cache
 
       - name: ⬇️ Install Application
         run: |
@@ -101,12 +104,14 @@ jobs:
           POSTGRES_USER: postgres
           POSTGRES_PASSWORD: postgres
           POSTGRES_DB: postgres
-          KHOJ_DEBUG: "False"             # To disable prompt tracer
           KHOJ_TELEMETRY_DISABLE: "True"  # To disable telemetry for tests
         run: |
           # Start Khoj server in background
           khoj --anonymous-mode --non-interactive &
 
+          # Start code sandbox
+          npm run dev --prefix cohere-terrarium &
+
           # Wait for server to be ready
           timeout=120
           while ! curl -s http://localhost:42110/api/health > /dev/null; do