Every hour
Get an analysis of each new earnings report compared with past quarters
When a new earnings report lands in your Drive folder, it is indexed and you get an email comparing it with earlier quarters.
- Runs
- Every hour
- Apps
- Google Drive, Pinecone
- AI
- Yes, uses the built-in AI allowance
- Access
- Drive read; Pinecone read+write
Send this to your assistant
Create a ClickRuntime automation: every hour, check my Drive Earnings folder for new reports, index them in Pinecone, and email me an analysis of revenue, margins and guidance compared with earlier quarters.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
Reading an earnings report properly means holding last quarter's numbers and commentary in your head while you read this one. Analysts covering several companies rarely have time to do that for each release, so comparisons stay shallow.
Investors, analysts and finance teams use it to get a first comparison as soon as a report is saved, with the earlier quarters' wording pulled from their own archive.
What you get out of it
Comparison is done for you
Each new report is set against what the company said in earlier quarters.
Your archive becomes useful
Every report you save makes later comparisons richer.
Arrives as soon as you file it
Saving the PDF to the folder is the only step.
Grounded in the documents
The analysis quotes the reports themselves, so you can check each point.
How it works
What happens, step by step
Every hour, ClickRuntime checks your Drive folder for reports added since its last check.
Each new report is read, split into chunks and added to your Pinecone index.
Passages from the same company's earlier reports are found in the index.
AI compares the new report with those passages, and the analysis is emailed to you.
Before it runs live
- Connect Google Drive
- Connect Pinecone
What you get
Build your own
Need it to work differently?
Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.
Changes you can ask for
- Act only on the items that match your own rules, and skip the rest
- Change what the AI looks for, or how it writes the result
- Add another app, for example also send it to Slack
- Combine it with other Google Drive and Pinecone steps into one automation
Under the hood
The code that runs this automation
import json
from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from clickruntime import on_trigger, report_fetched, credentials, http, state, notify, ai
FOLDER_Q = "'your-folder-id' in parents and mimeType='application/vnd.google-apps.document'"
HOST, NS = "https://docs-abc123.svc.aped-1234.pinecone.io", "company" # your index host and namespace
def search(text, k=5):
r = http.post(f"{HOST}/records/namespaces/{NS}/search", json={"query": {"inputs": {"text": text}, "top_k": k}}, headers={
"Api-Key": credentials.secret("PINECONE_API_KEY"), "X-Pinecone-API-Version": "2025-04"}).json()
return [h["fields"] for h in r["result"]["hits"]]
def upsert(records):
http.post(f"{HOST}/records/namespaces/{NS}/upsert", data="\n".join(json.dumps(r) for r in records[:96]), headers={
"Api-Key": credentials.secret("PINECONE_API_KEY"), "X-Pinecone-API-Version": "2025-04", "Content-Type": "application/x-ndjson"}).raise_for_status()
@on_trigger
def run(event):
drive = build("drive", "v3", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False).files()
new = drive.list(q=f"{FOLDER_Q} and createdTime > '{state.get('since') or '2026-01-01T00:00:00Z'}'",
fields="files(id,name,createdTime)").execute()["files"]
report_fetched(len(new))
if not new:
return {"new": 0}
for f in new:
text = drive.export(fileId=f["id"], mimeType="text/plain").execute().decode("utf-8", "ignore")
past = "\n".join(f"[{h['file_name']}] {h['chunk_text']}" for h in search(f"{f['name'].split()[0]} revenue margin guidance", 8))
upsert([{"_id": f"{f['id']}#{n}", "chunk_text": text[i:i + 1500], "file_name": f["name"]} for n, i in enumerate(range(0, len(text), 1500))])
notify.email_me(f"Earnings analysis: {f['name']}", ai.generate("Analyse this earnings report (revenue, margins, guidance, "
f"tone) and compare it with the earlier quarters.\nNEW:\n{text[:12000]}\nEARLIER:\n{past}", max_output_tokens=1200).text)
state.set("since", max(f["createdTime"] for f in new))FAQ
Common questions
Does it read PDFs?
What does the email cover?
Can it cover several companies?
What permissions does it need?
Does it need AI?
How many runs does it use?
Can I change how it works?
Related
You might also like
Draft replies to support emails from your Drive help docs
Each new support email gets a draft reply in Gmail, written from the help documents you keep in Drive.
See how it worksGet an accounting summary for each new EDI or export file in Drive
When a new EDI or accounting export lands in your Drive folder, it is indexed and you get an email summarising its bookings.
See how it worksKeep a Pinecone index in step with a Drive folder
New and edited files in your Drive folder are added to Pinecone within minutes, and files you remove are taken out of the index.
See how it worksKeep exploring
Set up “Get an analysis of each new earnings report compared with past quarters” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.