Launch Outbound When Target Accounts Add or Drop a Competitor

Part 1: Before you start

1. 1.Install the Clay CLI

   Use version 1.3.1 or later, installed from Clay's own instructions. This page does not include an install command because the CLI reference it was written from does not list one. You also need jq, which the script uses to read the JSON the CLI prints.

2. 2.Log in to your workspace

   Browser login is the default. Use the device flow on a headless machine. A static key in the CLAY_API_KEY environment variable also works. Workflow commands need the terracotta:cli scope, so an auth error that names it means your login cannot manage workflows.

   Log in with a browser

   $ clay loginCopy

   Log in on a headless machine

   $ clay login --deviceCopy

   Confirm who you are logged in as

   $ clay whoamiCopy

3. 3.Pick the workspace to build in

   The workflow is created in your active workspace. Switch first if you belong to more than one.

   List workspaces

   $ clay workspaces listCopy

   Show the active workspace

   $ clay workspaces currentCopy

   Switch workspace

   $ clay workspaces switch <workspaceId>Copy

4. 4.Find your action keys

   Action package ids and keys are specific to your workspace. Save the catalog, search it for a technographic lookup (for example BuiltWith), an AI text action, a find-people action, your sequencer, and your CRM update action, then paste their ids into the top of the script. Skip "clay workflows actions test": it spends credits.

   Save the action catalog

   $ clay workflows actions list > catalog.jsonCopy

   Search the catalog

   $ grep -Eio '"[^"]*(builtwith|technolog|hg insights|use ai|generate|find people|apollo|instantly|smartlead|hubspot|salesforce)[^"]*"' catalog.json | sort -uCopy

   See an action's inputs and outputs

   $ clay workflows actions schema <packageId> <actionKey>Copy

5. 5.Write your tool lists and add the CRM fields

   List your direct competitors and the tools that pair well with yours, using the names your technographic provider returns. Add company properties for detected technologies and last technology change in HubSpot or Salesforce, so each month compares against the last.

6. 6.Connect your sequencer and make a test campaign

   Connect Instantly or Smartlead inside Clay and create an empty campaign for testing, so early runs do not land in a live sequence.

Part 2: Workflow spec

What the script builds: Technology change outbound.

1. 1

   Pull current technologies

   action

   Looks up the technologies currently detected on the domain, with first-detected and last-detected dates where the provider returns them.

   Reads

   company_domain

   Writes

   current_technologies

   Verify in your workspace: Which technographic providers you can use depends on your Clay workspace and plan. BuiltWith detects website technologies; HG Insights-style install data, where available to you, can cover tools that do not show on the site.
2. 2

   Classify the change and write an opener

   action

   An AI text action compares the two lists against your competitor and complement lists and returns the change type, the tool, and an opener.

   Reads

   company_domainprevious_technologiescurrent_technologiestarget_title

   Writes

   change_typetoolopener

   Prompt

   Copy

   Compare two technology lists for {{company_domain}}. Last month: {{previous_technologies}} Now: {{current_technologies}} Competitors: {{your_competitor_list}} Complementary tools: {{your_complement_list}} Return JSON with change_type (dropped_competitor, added_competitor, added_complement, or none), tool (the tool that changed, or empty), and opener (one sentence under 25 words for a cold email to a {{target_title}} that relates to the change category). If last month's list is empty, return change_type none. The opener must not say how the change was detected or claim to know why they changed. No em dashes.
3. 3

   Find the contact

   action

   Finds one person in the target role at the account, with a work email. Runs only when change_type is not none.

   Reads

   company_domaintarget_title

   Writes

   first_namelast_nametitleemail

   Verify in your workspace: One run handles one contact. The "changed" rule needs a run condition, which the CLI help does not document, so set it in the Clay UI. Skip customers and open deals before uploading, or add a CRM lookup step.
4. 4

   Add to the sequence

   action

   Adds the contact to your Instantly or Smartlead campaign with the opener, change type, and owner as custom fields.

   Reads

   emailfirst_namelast_namecompany_nameopenerchange_typeowner_email

   Writes

   Sequencer lead
5. 5

   Save the new list to the CRM

   action

   Writes the current technology list, the change type, and the date to the company record so next month compares against it. Runs for every account.

   Reads

   crm_company_idcurrent_technologieschange_type

   Writes

   CRM record

Part 3: Build script

Creates the workflow, the CSV trigger, and five steps, then pauses so you can map step inputs and the change condition. It validates the graph, offers one test run, and asks before publishing.

Save it as build-tech-change-outbound.sh, fill in the 10 action ids at the top, then run bash build-tech-change-outbound.sh.

1#!/usr/bin/env bash2# Builds the "Technology change outbound" Clay workflow3# in YOUR Clay workspace, using YOUR Clay CLI login.4# Written against Clay CLI v1.3.1. Not run or tested by GTM Playbooks.5# Lines tagged VERIFY use a shape the CLI help does not document.6set -euo pipefail7 8# Copy these from catalog.json (see "Find your action keys").9TECH_PACKAGE_ID=""      # BuiltWith or another technology lookup10TECH_ACTION_KEY=""11CLASSIFY_PACKAGE_ID=""  # Use AI or another AI text action12CLASSIFY_ACTION_KEY=""13CONTACT_PACKAGE_ID=""   # Find people at a company (by title)14CONTACT_ACTION_KEY=""15SEQUENCER_PACKAGE_ID="" # Instantly or Smartlead: add lead to campaign16SEQUENCER_ACTION_KEY=""17CRM_PACKAGE_ID=""       # HubSpot or Salesforce: update company18CRM_ACTION_KEY=""19 20# One input to test before real traffic. Use yourself or a teammate.21TEST_ROW='{"company_domain":"","company_name":"","crm_company_id":"","owner_email":"","previous_technologies":"","target_title":""}'22 23for v in TECH_PACKAGE_ID TECH_ACTION_KEY CLASSIFY_PACKAGE_ID CLASSIFY_ACTION_KEY CONTACT_PACKAGE_ID CONTACT_ACTION_KEY SEQUENCER_PACKAGE_ID SEQUENCER_ACTION_KEY CRM_PACKAGE_ID CRM_ACTION_KEY; do24  [[ -n "${!v}" ]] || { echo "Set $v at the top of this script." >&2; exit 1; }25done26command -v clay > /dev/null || { echo "Clay CLI not found on PATH." >&2; exit 1; }27command -v jq > /dev/null || { echo "jq is required to read CLI output." >&2; exit 1; }28clay whoami > /dev/null || { echo "Not logged in. Run: clay login" >&2; exit 1; }29 30# VERIFY: only "workflows create" documents an "id" field in its output.31read_id() {32  local id33  id=$(jq -r '.id // empty' "$1")34  [[ -n "$id" ]] || { echo "No id found in $1. Open it and adjust read_id." >&2; exit 1; }35  echo "$id"36}37 38mkdir -p clay-tech-change-outbound39cd clay-tech-change-outbound40 41echo "1/9 Create the workflow"42clay workflows create --name "Technology change outbound" > workflow.json43WF_ID=$(read_id workflow.json)44WF_URL=$(jq -r '.url // empty' workflow.json)45 46echo "2/9 Add the CSV upload trigger"47# VERIFY: triggerType "csv_upload" is inferred; the help does not show it.48clay workflows triggers create "$WF_ID" --input '{"triggerType":"csv_upload"}' > trigger.json49TRG_ID=$(read_id trigger.json)50 51echo "3/9 Step 1: pull current technologies"52# VERIFY: help shows nodeType and name only; actionPackageId and actionKey are a guess.53STEP1=$(jq -nc --arg p "$TECH_PACKAGE_ID" --arg k "$TECH_ACTION_KEY" '{nodeType: "tool", name: "Pull current technologies", actionPackageId: $p, actionKey: $k}')54clay workflows nodes create "$WF_ID" --input "$STEP1" > step1.json55STEP1_ID=$(read_id step1.json)56 57echo "4/9 Step 2: classify the change and write an opener"58# VERIFY: action fields inside "step" are inferred from the documented utility example.59STEP2=$(jq -nc --arg n "$STEP1_ID" --arg p "$CLASSIFY_PACKAGE_ID" --arg k "$CLASSIFY_ACTION_KEY" '{target: {type: "after-node", nodeId: $n}, step: {kind: "action", actionPackageId: $p, actionKey: $k}}')60clay workflows nodes insert "$WF_ID" --input "$STEP2" > step2.json61STEP2_ID=$(read_id step2.json)62 63echo "5/9 Step 3: find the contact"64# VERIFY: same inferred insert shape as step 2.65STEP3=$(jq -nc --arg n "$STEP2_ID" --arg p "$CONTACT_PACKAGE_ID" --arg k "$CONTACT_ACTION_KEY" '{target: {type: "after-node", nodeId: $n}, step: {kind: "action", actionPackageId: $p, actionKey: $k}}')66clay workflows nodes insert "$WF_ID" --input "$STEP3" > step3.json67STEP3_ID=$(read_id step3.json)68 69echo "6/9 Step 4: add to the sequence"70# VERIFY: same inferred insert shape as step 2.71STEP4=$(jq -nc --arg n "$STEP3_ID" --arg p "$SEQUENCER_PACKAGE_ID" --arg k "$SEQUENCER_ACTION_KEY" '{target: {type: "after-node", nodeId: $n}, step: {kind: "action", actionPackageId: $p, actionKey: $k}}')72clay workflows nodes insert "$WF_ID" --input "$STEP4" > step4.json73STEP4_ID=$(read_id step4.json)74 75echo "7/9 Step 5: save the new list to the crm"76# VERIFY: same inferred insert shape as step 2.77STEP5=$(jq -nc --arg n "$STEP4_ID" --arg p "$CRM_PACKAGE_ID" --arg k "$CRM_ACTION_KEY" '{target: {type: "after-node", nodeId: $n}, step: {kind: "action", actionPackageId: $p, actionKey: $k}}')78clay workflows nodes insert "$WF_ID" --input "$STEP5" > step5.json79clay workflows graph get "$WF_ID" --mode full > graph.json80 81echo "8/9 Map step inputs"82cat <<EOF83 84Step inputs are specific to your workspace. Map them before validating:85  Step 1 tech:      company_domain86  Step 2 classify:  previous_technologies, current list from step 1,87                    target_title, and the prompt with your tool lists88  Step 3 contact:   company_domain and target_title; add a run condition89                    so steps 3 and 4 only run when change_type is not none90  Step 4 sequencer: email, name, company, opener, change_type, owner91  Step 5 CRM:       crm_company_id, current list, change_type, today92Map them in the Clay UI${WF_URL:+ at $WF_URL}, or per node with:93  clay workflows nodes get $WF_ID <nodeId>94  clay workflows nodes update $WF_ID <nodeId> --input node.json95graph.json in this folder shows the current nodes and edges.96 97EOF98read -r -p "Press Enter when inputs are mapped. "99 100echo "9/9 Validate, test once, publish"101clay workflows graph validate "$WF_ID"102clay workflows diagram "$WF_ID"103 104if jq -e 'all(.[]; . != "")' <<< "$TEST_ROW" > /dev/null; then105  read -r -p "Run TEST_ROW once? It can spend Clay credits, add a lead to your sequencer, and update your CRM. [y/N] " answer106  if [[ "$answer" == [yY] ]]; then107    clay workflows runs test "$WF_ID" --inputs "$TEST_ROW" > test-run.json108    echo "Saved test-run.json. Check each step with: clay workflows runs steps $WF_ID <runId>"109  fi110else111  echo "TEST_ROW is empty, skipping the test run."112fi113 114read -r -p "Publish the workflow now? [y/N] " answer115if [[ "$answer" == [yY] ]]; then116  clay workflows publish "$WF_ID" --name v1117fi118 119echo "Workflow $WF_ID, CSV upload trigger $TRG_ID. All responses are saved in $(pwd)."

Part 4: Account CSV

Save this as clay-tech-change-outbound/accounts.csv and replace the sample row with your export. Keep the headers exactly as shown, because they become the trigger inputs. Leave previous_technologies empty on the first run; that run only saves a baseline.

1company_domain,company_name,crm_company_id,owner_email,previous_technologies,target_title2example.com,Example Co,1234567890,owner@yourdomain.com,Google Analytics; Intercom; CompetitorX,Head of Customer Support

Part 5: Run it on your accounts

After publishing, upload the CSV to the trigger and start with a few rows. Each row is one run.

Verify in your workspace

The Clay CLI help does not document these details. Check each one before you rely on the build.

• The CSV trigger type "csv_upload" is inferred. If "triggers create" exits with code 2 (validation), check which trigger types your workspace accepts.
• The help documents "nodes create" with nodeType and name only. If it rejects actionPackageId and actionKey, create the node with a name only and pick the action in the Clay UI.
• The reference says action steps take actionPackageId and actionKey but shows only a utility example for "nodes insert", so the placement of those fields inside "step" is inferred.
• Only "workflows create" documents an id field in its response. The script reads .id from trigger and node responses too and stops if it is missing.
• Package ids and action keys differ by workspace and depend on which integrations you have connected. Copy them from your catalog; this page does not guess them.
• Step input mapping is dynamic per workspace. The CLI path is "nodes get" then "nodes update", where incomingEdges is a full replacement. The argument order for "nodes get" is inferred from "nodes update".
• The help does not say whether step 1 connects to the trigger automatically. "clay workflows graph validate" reports a disconnected graph.
• Technology names must match between your lists and the provider output. Check a few lookups by hand before trusting the classification.
• "runs test" without --live is assumed to run the draft. The reference lists --live without describing it.
• Workflow runs can spend Clay credits and write to connected tools. Exit code 3 means re-run clay login, and exit code 4 means you are rate limited (wait for details.retryAfter).