diff --git a/project/AI/index.md b/project/AI/index.md
index d1923b8..4d7a691 100644
--- a/project/AI/index.md
+++ b/project/AI/index.md
@@ -25,8 +25,11 @@ OntoGPT implements two different strategies for knowledge extraction: SPIRES and
 - Takes two inputs - 1) LinkML schema 2) free text, and outputs knowledge in a structure conformant with the supplied schema in JSON, YAML, RDF or OWL formats
 - Source: part of [OntoGPT](https://github.com/monarch-initiative/ontogpt)
 - [Templates (see sidebar)](https://monarch-initiative.github.io/ontogpt/core/)
+- [Blog post](https://monarchinit.medium.com/spires-building-structured-knowledge-bases-from-unstructured-text-using-large-language-models-eb68c12dea75)
 - Preprint: Caufield JH, Hegde H, Emonet V, Harris NL, Joachimiak MP, Matentzoglu N, Kim H, Moxon SAT, Reese JT, Haendel MA, Robinson PN, Mungall CJ. Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning. arXiv [cs.AI]. 2023. [http://arxiv.org/abs/2304.02711](https://arxiv.org/abs/2304.02711)
 
+<img src="https://miro.medium.com/v2/resize:fit:952/format:webp/1*-s9p8cWQkvgjzmftpVYxNA.png" width="300"/>
+
 ***SPINDOCTOR (Structured Prompt Interpolation of Natural Language Descriptions Of Controlled Terms for Ontology Reporting)****
 - Uses GPT models to perform gene set function summarization as a complement to standard enrichment analysis
 - Source: part of [OntoGPT](https://github.com/monarch-initiative/ontogpt)