Trouble getting array to create single output to Airtable

How To
1

I’m trying to automate my blog process using AirTable as the DB connected to Make.com. I’m having trouble getting one of the scenarios to work. Here’s what I’m trying to achieve in this scenario, titled Find Research Articles:

Goal:
Automatically search PubMed for recent research articles on a given topic, format each into an APA-style citation, and aggregate them into a single field in Airtable.

Scenario Workflow Breakdown

1. Airtable Trigger: (FUNCTIONING)

Watch records in the blog post table where:

  • Include Research = Yes
  • Needs Research = Yes
  • Status: Ready
    This triggers the workflow when a blog post requires citations.

2. HTTP Module (PubMed ESearch): (FUNCTIONING)

  • GET request to ESearch endpoint:
    https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi
    Parameters:
    • db=pubmed
    • term={{Topic}} (or a more specific query)
    • retmax=4
    • retmode=json
      Output: idlist[] – an array of PubMed IDs.

3. Iterator (over PubMed IDs): (FUNCTIONING)

  • Iterates over the array of PubMed IDs from HTTP#1.
  • Each UID becomes a single bundle to process next.

4. HTTP Module (PubMed ESummary): (FUNCTIONING)

  • GET request to ESummary endpoint:
https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi

Parameters:

  • db=pubmed
  • id={{UID from iterator}}
  • retmode=json
    Output: Full article metadata (title, journal, date, authors, etc.)

5. OpenAI Module – Format Citation (FUNCTIONING)
Sends metadata from HTTP#2 into OpenAI with the prompt:

You are an expert scientific citation formatter.  
You will receive a JSON array of PubMed article objects under the key "articles".  
For each article in order, output an APA‐style citation on its own line:
- Use “et al.” if there are more than 3 authors.
- Italicize journal titles and volume numbers.
- Include a clickable PubMed link via the PMID.

Here is the JSON:
```json
{{7.data.result.`40564122`}}

Output: One formatted citation (text string).

This next part is the problem:
The output is always 4 bundles, not 1

6. Text Aggregator – Combine All Citations (NOT WORKING)

  • Module: Tools → Text Aggregator
  • Settings:
    • Source Module: OpenAI
    • Field to Aggregate: choices.message.content
    • Separator: new line
      Output: All citations combined into one text block

7. Airtable – Update Record (NOT WORKING - The Formatted Reference field is overwritten 3 times, so only 1 citation (the last output) remains in the Airtable field, instead of the combined 4 citations.

  • Fields Updated:
    • Formatted References ← Aggregated citations
    • Research Complete = Yes

If anyone has ANY suggestions, please let me know. I’m open to any method that will achieve my goals.

Thanks in advance!!
-Shawn

2

We’d love to help, however, you have not provided sufficient information to demonstrate the problem that would allow us to reproduce the scenario and any issue/s and/or error/s.

To allow others to assist you with your scenario, please provide the following:

1. All Relevant Screenshots

We need to see what you’re working with to give you the best advice. Screenshots are extremely important because Make is a visual editor — a picture provides us with more context.

It would help us identify the issue by having screenshots of:

  • the full scenario,
  • any error messages,
  • individual module fields,
  • relevant filter settings (conditions), and
  • each module’s output bundles
  • any external services (spreadsheet headers, sample data, regex101.com, etc.)

2. Scenario Blueprint

Please export the scenario blueprint. Providing your scenario blueprint file will allow others to quickly recreate and see how you have set up the mappings in each module, and also allows us take screenshots or provide module exports of any solutions we have for you in return - this would greatly benefit you in implementing our suggestions as you can simply paste module exports back into your scenario editor!

To export your scenario blueprint, click the three dots at the bottom of the editor then choose ‘Export Blueprint’.

3. Module Output Bundles

Please provide the output bundles of each of the relevant modules by running the scenario (you can also get this without re-running your scenario from the History tab).

Click on the white speech bubbles on the top-right of each module and select “Download input/output bundles”.

490×338 23.5 KB

A. Upload as a Text File

Save each bundle contents in a plain text editor (without formatting) as a bundle.txt file.

You can upload the file here by clicking on this button:

B. Insert as Formatted Code Block

If you are unable to upload files on this forum, alternatively you can paste the formatted bundles.

To provide code/text using Markdown format, you can type a code fence.
Add three backticks ``` in a separate line before and after the content, like this,

```
text goes here
```

Alternatively, you can upload your file and share the public link** —
(this method is only recommended for large files exceeding the forum upload limit)

Providing the input/output bundles will allow others to replicate what is going on in the scenario, especially if there are complex data structures (nested arrays and collections) or if external services are involved, and help you with mapping the raw property names from collections.

Sharing these details will make it easier for others to assist you.